io_uring: parse check_cq out of wq waiting

We already avoid flushing overflows in io_cqring_wait_schedule() but
only return an error for the outer loop to handle it. Minimise it even
further by moving all ->check_cq parsing there.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/9dfcec3121013f98208dbf79368d636d74e1231a.1672916894.git.asml.silence@gmail.comSigned-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/io_uring.c

@@ -2471,21 +2471,13 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 					  ktime_t *timeout)
 {
 	int ret;
-	unsigned long check_cq;
 
+	if (unlikely(READ_ONCE(ctx->check_cq)))
+		return 1;
 	/* make sure we run task_work before checking for signals */
 	ret = io_run_task_work_sig(ctx);
 	if (ret || io_should_wake(iowq))
 		return ret;
-
-	check_cq = READ_ONCE(ctx->check_cq);
-	if (unlikely(check_cq)) {
-		/* let the caller flush overflows, retry */
-		if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT))
-			return 1;
-		if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))
-			return -EBADR;
-	}
 	if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS))
 		return -ETIME;
 
@@ -2551,13 +2543,25 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 
 	trace_io_uring_cqring_wait(ctx, min_events);
 	do {
-		if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
-			finish_wait(&ctx->cq_wait, &iowq.wq);
-			io_cqring_do_overflow_flush(ctx);
-		}
+		unsigned long check_cq;
+
 		prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
 						TASK_INTERRUPTIBLE);
 		ret = io_cqring_wait_schedule(ctx, &iowq, &timeout);
+
+		check_cq = READ_ONCE(ctx->check_cq);
+		if (unlikely(check_cq)) {
+			/* let the caller flush overflows, retry */
+			if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)) {
+				finish_wait(&ctx->cq_wait, &iowq.wq);
+				io_cqring_do_overflow_flush(ctx);
+			}
+			if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)) {
+				ret = -EBADR;
+				break;
+			}
+		}
+
 		if (__io_cqring_events_user(ctx) >= min_events)
 			break;
 		cond_resched();