commit bcb0fda3c2da9fe4721d3e73d80e778c038e7d27 upstream.
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: d803d123948f ("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... Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sumanth Gavini sumanth.gavini@yahoo.com --- Changes in v2: - Removed the extra space before commit-id in message, No codes changes - Link to v1:https://lore.kernel.org/all/20250809182636.209767-1-sumanth.gavini@yahoo.com...
--- io_uring/rw.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/io_uring/rw.c b/io_uring/rw.c index 4ff3442ac2ee..6a84c4a39ce9 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -326,11 +326,10 @@ 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_PARTIAL_IO; - return; - } - req->cqe.res = res; + else + req->cqe.res = res; }
/* order with io_iopoll_complete() checking ->iopoll_completed */