io_uring: refactor DEFER_TASKRUN multishot checks

BugLink: https://bugs.launchpad.net/bugs/2065912

Commit e0e4ab52d17096d96c21a6805ccd424b283c3c6d upstream.

We disallow DEFER_TASKRUN multishots from running by io-wq, which is
checked by individual opcodes in the issue path. We can consolidate all
it in io_wq_submit_work() at the same time moving the checks out of the
hot path.

Suggested-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/e492f0f11588bb5aa11d7d24e6f53b7c7628afdb.1709905727.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Manuel Diewald <manuel.diewald@canonical.com>
Signed-off-by: Roxana Nicolescu <roxana.nicolescu@canonical.com>

io_uring/io_uring.c

@@ -949,6 +949,8 @@ bool io_fill_cqe_req_aux(struct io_kiocb *req, bool defer, s32 res, u32 cflags)
 	u64 user_data = req->cqe.user_data;
 	struct io_uring_cqe *cqe;
 
+	lockdep_assert(!io_wq_current_is_worker());
+
 	if (!defer)
 		return __io_post_aux_cqe(ctx, user_data, res, cflags, false);
 
@@ -1950,6 +1952,24 @@ fail:
 		goto fail;
 	}
 
+	/*
+	 * If DEFER_TASKRUN is set, it's only allowed to post CQEs from the
+	 * submitter task context. Final request completions are handed to the
+	 * right context, however this is not the case of auxiliary CQEs,
+	 * which is the main mean of operation for multishot requests.
+	 * Don't allow any multishot execution from io-wq. It's more restrictive
+	 * than necessary and also cleaner.
+	 */
+	if (req->flags & REQ_F_APOLL_MULTISHOT) {
+		err = -EBADFD;
+		if (!file_can_poll(req->file))
+			goto fail;
+		err = -ECANCELED;
+		if (io_arm_poll_handler(req, issue_flags) != IO_APOLL_OK)
+			goto fail;
+		return;
+	}
+
 	if (req->flags & REQ_F_FORCE_ASYNC) {
 		bool opcode_poll = def->pollin || def->pollout;
 

io_uring/net.c

@@ -78,19 +78,6 @@ struct io_sr_msg {
  */
 #define MULTISHOT_MAX_RETRY	32
 
-static inline bool io_check_multishot(struct io_kiocb *req,
-				      unsigned int issue_flags)
-{
-	/*
-	 * When ->locked_cq is set we only allow to post CQEs from the original
-	 * task context. Usual request completions will be handled in other
-	 * generic paths but multipoll may decide to post extra cqes.
-	 */
-	return !(issue_flags & IO_URING_F_IOWQ) ||
-		!(req->flags & REQ_F_APOLL_MULTISHOT) ||
-		!req->ctx->task_complete;
-}
-
 int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_shutdown *shutdown = io_kiocb_to_cmd(req, struct io_shutdown);
@@ -837,9 +824,6 @@ int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
 	    (sr->flags & IORING_RECVSEND_POLL_FIRST))
 		return io_setup_async_msg(req, kmsg, issue_flags);
 
-	if (!io_check_multishot(req, issue_flags))
-		return io_setup_async_msg(req, kmsg, issue_flags);
-
 retry_multishot:
 	if (io_do_buffer_select(req)) {
 		void __user *buf;
@@ -935,9 +919,6 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 	    (sr->flags & IORING_RECVSEND_POLL_FIRST))
 		return -EAGAIN;
 
-	if (!io_check_multishot(req, issue_flags))
-		return -EAGAIN;
-
 	sock = sock_from_file(req->file);
 	if (unlikely(!sock))
 		return -ENOTSOCK;
@@ -1386,8 +1367,6 @@ int io_accept(struct io_kiocb *req, unsigned int issue_flags)
 	struct file *file;
 	int ret, fd;
 
-	if (!io_check_multishot(req, issue_flags))
-		return -EAGAIN;
 retry:
 	if (!fixed) {
 		fd = __get_unused_fd_flags(accept->flags, accept->nofile);

io_uring/rw.c

@@ -932,8 +932,6 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 	 */
 	if (!file_can_poll(req->file))
 		return -EBADFD;
-	if (issue_flags & IO_URING_F_IOWQ)
-		return -EAGAIN;
 
 	ret = __io_read(req, issue_flags);