io_uring: gate iowait schedule on having pending requests

Commit 7b72d661f1 upstream.

A previous commit made all cqring waits marked as iowait, as a way to
improve performance for short schedules with pending IO. However, for
use cases that have a special reaper thread that does nothing but
wait on events on the ring, this causes a cosmetic issue where we
know have one core marked as being "busy" with 100% iowait.

While this isn't a grave issue, it is confusing to users. Rather than
always mark us as being in iowait, gate setting of current->in_iowait
to 1 by whether or not the waiting task has pending requests.

Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/io-uring/CAMEGJJ2RxopfNQ7GNLhr7X9=bHXKo+G5OOe0LUq=+UgLXsv1Xg@mail.gmail.com/
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217699
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217700
Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Reported-by: Phil Elwell <phil@raspberrypi.com>
Tested-by: Andres Freund <andres@anarazel.de>
Fixes: 8a796565ce ("io_uring: Use io_schedule* in cqring wait")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

io_uring/io_uring.c

@@ -7802,12 +7802,21 @@ static int io_run_task_work_sig(void)
 	return -EINTR;
 }
 
+static bool current_pending_io(void)
+{
+	struct io_uring_task *tctx = current->io_uring;
+
+	if (!tctx)
+		return false;
+	return percpu_counter_read_positive(&tctx->inflight);
+}
+
 /* when returns >0, the caller should retry */
 static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 					  struct io_wait_queue *iowq,
 					  ktime_t *timeout)
 {
-	int token, ret;
+	int io_wait, ret;
 
 	/* make sure we run task_work before checking for signals */
 	ret = io_run_task_work_sig();
@@ -7818,15 +7827,17 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 		return 1;
 
 	/*
-	 * Use io_schedule_prepare/finish, so cpufreq can take into account
+	 * Mark us as being in io_wait if we have pending requests, so cpufreq
-	 * that the task is waiting for IO - turns out to be important for low
+	 * can take into account that the task is waiting for IO - turns out
-	 * QD IO.
+	 * to be important for low QD IO.
 	 */
-	token = io_schedule_prepare();
+	io_wait = current->in_iowait;
+	if (current_pending_io())
+		current->in_iowait = 1;
 	ret = 1;
 	if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS))
 		ret = -ETIME;
-	io_schedule_finish(token);
+	current->in_iowait = io_wait;
 	return ret;
 }