--- /dev/null
+From 08130195d34476bfbc63c53532f95245abfcfe6d Mon Sep 17 00:00:00 2001
+From: Jens Axboe <axboe@kernel.dk>
+Date: Tue, 1 Aug 2023 08:42:37 -0600
+Subject: io_uring: gate iowait schedule on having pending requests
+
+From: Jens Axboe <axboe@kernel.dk>
+
+Commit 7b72d661f1f2f950ab8c12de7e2bc48bdac8ed69 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: 8a796565cec3 ("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 | 23 +++++++++++++++++------
+ 1 file changed, 17 insertions(+), 6 deletions(-)
+
+--- a/io_uring/io_uring.c
++++ b/io_uring/io_uring.c
+@@ -2349,12 +2349,21 @@ int io_run_task_work_sig(struct io_ring_
+ return 0;
+ }
+
++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;
+ unsigned long check_cq;
+
+ /* make sure we run task_work before checking for signals */
+@@ -2372,15 +2381,17 @@ static inline int io_cqring_wait_schedul
+ }
+
+ /*
+- * Use io_schedule_prepare/finish, so cpufreq can take into account
+- * that the task is waiting for IO - turns out to be important for low
+- * QD IO.
++ * Mark us as being in io_wait if we have pending requests, so cpufreq
++ * can take into account that the task is waiting for IO - turns out
++ * 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;
+ }
+