io_uring: wake up optimisations

Flush completions is done either from the submit syscall or by the
task_work, both are in the context of the submitter task, and when it
goes for a single threaded rings like implied by ->task_complete, there
won't be any waiters on ->cq_wait but the master task. That means that
there can be no tasks sleeping on cq_wait while we run
__io_submit_flush_completions() and so waking up can be skipped.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/60ad9768ec74435a0ddaa6eec0ffa7729474f69f.1673274244.git.asml.silence@gmail.comSigned-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/io_uring.c

@@ -621,6 +621,25 @@ static inline void __io_cq_unlock_post(struct io_ring_ctx *ctx)
 	io_cqring_wake(ctx);
 }
 
+static inline void __io_cq_unlock_post_flush(struct io_ring_ctx *ctx)
+	__releases(ctx->completion_lock)
+{
+	io_commit_cqring(ctx);
+	__io_cq_unlock(ctx);
+	io_commit_cqring_flush(ctx);
+
+	/*
+	 * As ->task_complete implies that the ring is single tasked, cq_wait
+	 * may only be waited on by the current in io_cqring_wait(), but since
+	 * it will re-check the wakeup conditions once we return we can safely
+	 * skip waking it up.
+	 */
+	if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN)) {
+		smp_mb();
+		__io_cqring_wake(ctx);
+	}
+}
+
 void io_cq_unlock_post(struct io_ring_ctx *ctx)
 	__releases(ctx->completion_lock)
 {
@@ -1480,7 +1499,7 @@ static void __io_submit_flush_completions(struct io_ring_ctx *ctx)
 			}
 		}
 	}
-	__io_cq_unlock_post(ctx);
+	__io_cq_unlock_post_flush(ctx);
 
 	if (!wq_list_empty(&ctx->submit_state.compl_reqs)) {
 		io_free_batch_list(ctx, state->compl_reqs.first);