Commit bcb0fda3 authored Mar 05, 2025 by Jens Axboe

io_uring/rw: ensure reissue path is correctly handled for IOPOLL



The IOPOLL path posts CQEs when the io_kiocb is marked as completed,
so it cannot rely on the usual retry that non-IOPOLL requests do for
read/write requests.

If -EAGAIN is received and the request should be retried, go through
the normal completion path and let the normal flush logic catch it and
reissue it, like what is done for !IOPOLL reads or writes.

Fixes: d803d123 ("io_uring/rw: handle -EAGAIN retry at IO completion time")
Reported-by: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/io-uring/2b43ccfa-644d-4a09-8f8f-39ad71810f41@oracle.com/


Signed-off-by: Jens Axboe <axboe@kernel.dk>

parent 6ebf0518

io_uring/rw.c

+3 −4

Original line number	Diff line number	Diff line
		@@ -560,10 +560,9 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
		if (kiocb->ki_flags & IOCB_WRITE)
		io_req_end_write(req);
		if (unlikely(res != req->cqe.res)) {
		if (res == -EAGAIN && io_rw_should_reissue(req)) {
		if (res == -EAGAIN && io_rw_should_reissue(req))
		req->flags \|= REQ_F_REISSUE \| REQ_F_BL_NO_RECYCLE;
		return;
		}
		else
		req->cqe.res = res;
		}