io_uring: ensure deferred completions are posted for multishot

Commit 687b2bae0efff9b25e071737d6af5004e6e35af5 upstream.

Multishot normally uses io_req_post_cqe() to post completions, but when
stopping it, it may finish up with a deferred completion. This is fine,
except if another multishot event triggers before the deferred completions
get flushed. If this occurs, then CQEs may get reordered in the CQ ring,
and cause confusion on the application side.

When multishot posting via io_req_post_cqe(), flush any pending deferred
completions first, if any.

Cc: stable@vger.kernel.org # 6.1+
Reported-by: Norman Maurer <norman_maurer@apple.com>
Reported-by: Christian Mazakas <christian.mazakas@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 4f4ac40fc6059bf026794dc91ec366c7f7791bff..db592fa549b7386d1bc5431645ded200219a6bfe 100644 (file)
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -919,6 +919,14 @@ static bool __io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u
 {
        bool filled;
 
+       /*
+        * If multishot has already posted deferred completions, ensure that
+        * those are flushed first before posting this one. If not, CQEs
+        * could get reordered.
+        */
+       if (!wq_list_empty(&ctx->submit_state.compl_reqs))
+               __io_submit_flush_completions(ctx);
+
        io_cq_lock(ctx);
        filled = io_fill_cqe_aux(ctx, user_data, res, cflags);
        if (!filled && allow_overflow)