io_uring: reorder cqring_flush and wakeups

Unlike in the past, io_commit_cqring_flush() doesn't do anything that
may need io_cqring_wake() to be issued after, all requests it completes
will go via task_work. Do io_commit_cqring_flush() after
io_cqring_wake() to clean up __io_cq_unlock_post().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/ed32dcfeec47e6c97bd6b18c152ddce5b218403f.1692916914.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: isilence

io_uring/io_uring.c

@@ -629,28 +629,20 @@ static inline void io_cq_lock(struct io_ring_ctx *ctx)
 static inline void __io_cq_unlock_post(struct io_ring_ctx *ctx)
 {
 	io_commit_cqring(ctx);
-
-	if (ctx->task_complete) {
-		/*
-		 * ->task_complete implies that only current might be waiting
-		 * for CQEs, and obviously, we currently don't. No one is
-		 * waiting, wakeups are futile, skip them.
-		 */
-		io_commit_cqring_flush(ctx);
-	} else {
+	if (!ctx->task_complete) {
 		spin_unlock(&ctx->completion_lock);
-		io_commit_cqring_flush(ctx);
 		io_cqring_wake(ctx);
 	}
+	io_commit_cqring_flush(ctx);
 }
 
 static void io_cq_unlock_post(struct io_ring_ctx *ctx)
 	__releases(ctx->completion_lock)
 {
 	io_commit_cqring(ctx);
 	spin_unlock(&ctx->completion_lock);
-	io_commit_cqring_flush(ctx);
 	io_cqring_wake(ctx);
+	io_commit_cqring_flush(ctx);
 }
 
 /* Returns true if there are no backlogged entries after the flush */

io_uring/rw.c

@@ -985,9 +985,9 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags)
 
 static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
 {
-	io_commit_cqring_flush(ctx);
 	if (ctx->flags & IORING_SETUP_SQPOLL)
 		io_cqring_wake(ctx);
+	io_commit_cqring_flush(ctx);
 }
 
 void io_rw_fail(struct io_kiocb *req)