io_uring: add mshot helper for posting CQE32

Add a helper for posting 32 byte CQEs in a multishot mode and add a cmd
helper on top. As it specifically works with requests, the helper ignore
the passed in cqe->user_data and sets it to the one stored in the
request.

The command helper is only valid with multishot requests.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/c29d7720c16e1f981cfaa903df187138baa3946b.1750065793.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/io_uring.c

@@ -793,6 +793,21 @@ bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow)
 	return true;
 }
 
+static bool io_fill_cqe_aux32(struct io_ring_ctx *ctx,
+			      struct io_uring_cqe src_cqe[2])
+{
+	struct io_uring_cqe *cqe;
+
+	if (WARN_ON_ONCE(!(ctx->flags & IORING_SETUP_CQE32)))
+		return false;
+	if (unlikely(!io_get_cqe(ctx, &cqe)))
+		return false;
+
+	memcpy(cqe, src_cqe, 2 * sizeof(*cqe));
+	trace_io_uring_complete(ctx, NULL, cqe);
+	return true;
+}
+
 static bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res,
 			      u32 cflags)
 {
@@ -904,6 +919,31 @@ bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags)
 	return posted;
 }
 
+/*
+ * A helper for multishot requests posting additional CQEs.
+ * Should only be used from a task_work including IO_URING_F_MULTISHOT.
+ */
+bool io_req_post_cqe32(struct io_kiocb *req, struct io_uring_cqe cqe[2])
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	bool posted;
+
+	lockdep_assert(!io_wq_current_is_worker());
+	lockdep_assert_held(&ctx->uring_lock);
+
+	cqe[0].user_data = req->cqe.user_data;
+	if (!ctx->lockless_cq) {
+		spin_lock(&ctx->completion_lock);
+		posted = io_fill_cqe_aux32(ctx, cqe);
+		spin_unlock(&ctx->completion_lock);
+	} else {
+		posted = io_fill_cqe_aux32(ctx, cqe);
+	}
+
+	ctx->submit_state.cq_flush = true;
+	return posted;
+}
+
 static void io_req_complete_post(struct io_kiocb *req, unsigned issue_flags)
 {
 	struct io_ring_ctx *ctx = req->ctx;

io_uring/io_uring.h

@@ -81,6 +81,7 @@ void io_req_defer_failed(struct io_kiocb *req, s32 res);
 bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags);
 void io_add_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags);
 bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags);
+bool io_req_post_cqe32(struct io_kiocb *req, struct io_uring_cqe src_cqe[2]);
 void __io_commit_cqring_flush(struct io_ring_ctx *ctx);
 
 void io_req_track_inflight(struct io_kiocb *req);

io_uring/uring_cmd.c

@@ -328,3 +328,14 @@ int io_cmd_poll_multishot(struct io_uring_cmd *cmd,
 	ret = io_arm_apoll(req, issue_flags, mask);
 	return ret == IO_APOLL_OK ? -EIOCBQUEUED : -ECANCELED;
 }
+
+bool io_uring_cmd_post_mshot_cqe32(struct io_uring_cmd *cmd,
+				   unsigned int issue_flags,
+				   struct io_uring_cqe cqe[2])
+{
+	struct io_kiocb *req = cmd_to_io_kiocb(cmd);
+
+	if (WARN_ON_ONCE(!(issue_flags & IO_URING_F_MULTISHOT)))
+		return false;
+	return io_req_post_cqe32(req, cqe);
+}

io_uring/uring_cmd.h

@@ -17,6 +17,10 @@ void io_uring_cmd_cleanup(struct io_kiocb *req);
 bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx,
 				   struct io_uring_task *tctx, bool cancel_all);
 
+bool io_uring_cmd_post_mshot_cqe32(struct io_uring_cmd *cmd,
+				   unsigned int issue_flags,
+				   struct io_uring_cqe cqe[2]);
+
 void io_cmd_cache_free(const void *entry);
 
 int io_cmd_poll_multishot(struct io_uring_cmd *cmd,