[PATCH 5/6] io_uring/rw: add write support for IOCB_DIO_DEFER

[Jens Axboe <axboe@xxxxxxxxx>]

If the filesystem dio handler understands IOCB_DIO_DEFER, we'll get
a kiocb->ki_complete() callback with kiocb->dio_complete set. In that
case, rather than complete the IO directly through task_work, queue
up an intermediate task_work handler that first processes this
callback and then immediately completes the request.

For XFS, this avoids a punt through a workqueue, which is a lot less
efficient and adds latency to lower queue depth (or sync) O_DIRECT
writes.

Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
 io_uring/rw.c | 27 +++++++++++++++++++++++----
 1 file changed, 23 insertions(+), 4 deletions(-)

diff --git a/io_uring/rw.c b/io_uring/rw.c
index 1bce2208b65c..4657e11acf02 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -285,6 +285,14 @@ static inline int io_fixup_rw_res(struct io_kiocb *req, long res)
 
 void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts)
 {
+	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
+
+	if (rw->kiocb.dio_complete) {
+		long res = rw->kiocb.dio_complete(rw->kiocb.private);
+
+		io_req_set_res(req, io_fixup_rw_res(req, res), 0);
+	}
+
 	io_req_io_end(req);
 
 	if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) {
@@ -300,9 +308,11 @@ static void io_complete_rw(struct kiocb *kiocb, long res)
 	struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb);
 	struct io_kiocb *req = cmd_to_io_kiocb(rw);
 
-	if (__io_complete_rw_common(req, res))
-		return;
-	io_req_set_res(req, io_fixup_rw_res(req, res), 0);
+	if (!rw->kiocb.dio_complete) {
+		if (__io_complete_rw_common(req, res))
+			return;
+		io_req_set_res(req, io_fixup_rw_res(req, res), 0);
+	}
 	req->io_task_work.func = io_req_rw_complete;
 	__io_req_task_work_add(req, IOU_F_TWQ_LAZY_WAKE);
 }
@@ -312,6 +322,9 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
 	struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb);
 	struct io_kiocb *req = cmd_to_io_kiocb(rw);
 
+	if (rw->kiocb.dio_complete)
+		res = rw->kiocb.dio_complete(rw->kiocb.private);
+
 	if (kiocb->ki_flags & IOCB_WRITE)
 		kiocb_end_write(req);
 	if (unlikely(res != req->cqe.res)) {
@@ -914,7 +927,13 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags)
 		__sb_writers_release(file_inode(req->file)->i_sb,
 					SB_FREEZE_WRITE);
 	}
-	kiocb->ki_flags |= IOCB_WRITE;
+
+	/*
+	 * Set IOCB_DIO_DEFER, stating that our handler groks deferring the
+	 * completion to task context.
+	 */
+	kiocb->ki_flags |= IOCB_WRITE | IOCB_DIO_DEFER;
+	kiocb->dio_complete = NULL;
 
 	if (likely(req->file->f_op->write_iter))
 		ret2 = call_write_iter(req->file, kiocb, &s->iter);
-- 
2.40.1