Merge tag 'io_uring-6.5-2023-07-28' of git://git.kernel.dk/linux

Pull io_uring fix from Jens Axboe:
 "Just a single tweak to a patch from last week, to avoid having idle
  cqring waits be attributed as iowait"

* tag 'io_uring-6.5-2023-07-28' of git://git.kernel.dk/linux:
  io_uring: gate iowait schedule on having pending requests

1 files changed, 17 insertions, 6 deletions

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 89a611541bc4..f4591b912ea8 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2493,11 +2493,20 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx)
 	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)
 {
-	int token, ret;
+	int io_wait, ret;
 
 	if (unlikely(READ_ONCE(ctx->check_cq)))
 		return 1;
@@ -2511,17 +2520,19 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 		return 0;
 
 	/*
-	 * 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 = 0;
 	if (iowq->timeout == KTIME_MAX)
 		schedule();
 	else if (!schedule_hrtimeout(&iowq->timeout, HRTIMER_MODE_ABS))
 		ret = -ETIME;
-	io_schedule_finish(token);
+	current->in_iowait = io_wait;
 	return ret;
 }