io_uring/wait: wake real-time waiters from hard interrupt context

Since commit cebf123c634a ("io_uring: implement our own schedule timeout
handling"), a CQ wait with a timeout sleeps on io_uring's own hrtimer
instead of an hrtimer sleeper.  On PREEMPT_RT, an hrtimer that isn't
marked for hard interrupt expiry expires in the per-CPU ktimers thread,
which runs at SCHED_FIFO 1.  A real-time task waiting in io_uring_enter()
is therefore not woken at its deadline while any other real-time task is
runnable on its CPU: the wakeup waits until every one of them has blocked.

hrtimer sleepers, which schedule_hrtimeout_range_clock() used to give
io_uring, don't have this problem: __hrtimer_setup_sleeper() marks the
timer hard when the sleeping task is in a real-time or deadline class.
Both of io_uring's callbacks are fine in hard interrupt context:
io_cqring_timer_wakeup() sets a flag and calls wake_up_process(), and
io_cqring_min_timer_wakeup() only reads ring state, under RCU, before
doing the same or re-arming the timer.  Apply the sleeper rule to them.

Measured on a Jetson Orin Nano running 6.18.39-rt with this change
backported: a SCHED_FIFO 40 task waits in io_uring_enter() for 40,000
deadlines 500us apart, while a SCHED_FIFO 20 task runs bursts of up to
1ms on the same CPU.  Before, 6,647 wakeups were more than 100us late,
the latest by 1,040us, and 2,758 deadlines passed without a wakeup at
all.  After, none were more than 100us late and the latest was 18us.

This mirrors epoll: epoll_pwait2() waits on an hrtimer sleeper, so its
timeout is already hard for real-time tasks, and on the same setup it
was never more than 17us late.

Fixes: cebf123c634a ("io_uring: implement our own schedule timeout handling")
Cc: stable@vger.kernel.org
Assisted-by: LLM
Signed-off-by: Austin Schuh <austin.linux@gmail.com>
Link: https://patch.msgid.link/20261017171726.601443-1-austin.linux@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 13 insertions, 3 deletions

diff --git a/io_uring/wait.c b/io_uring/wait.c
index b7a0292767c7..fb1c082993a7 100644
--- a/io_uring/wait.c
+++ b/io_uring/wait.c
@@ -3,6 +3,7 @@
  * Waiting for completion events
  */
 #include <linux/kernel.h>
+#include <linux/sched/rt.h>
 #include <linux/sched/signal.h>
 #include <linux/io_uring.h>
 #include <linux/time_namespace.h>
@@ -120,23 +121,32 @@ out_wake:
 	return io_cqring_timer_wakeup(timer);
 }
 
+/* Same policy as for hrtimer sleepers, see __hrtimer_setup_sleeper(). */
+static enum hrtimer_mode io_cqring_timer_mode(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT) && rt_or_dl_task_policy(current))
+		return HRTIMER_MODE_ABS_HARD;
+	return HRTIMER_MODE_ABS;
+}
+
 static int io_cqring_schedule_timeout(struct io_wait_queue *iowq,
 				      clockid_t clock_id, ktime_t start_time)
 {
+	enum hrtimer_mode mode = io_cqring_timer_mode();
 	ktime_t timeout;
 
 	if (iowq->min_timeout) {
 		timeout = ktime_add_ns(iowq->min_timeout, start_time);
 		hrtimer_setup_on_stack(&iowq->t, io_cqring_min_timer_wakeup, clock_id,
-				       HRTIMER_MODE_ABS);
+				       mode);
 	} else {
 		timeout = iowq->timeout;
 		hrtimer_setup_on_stack(&iowq->t, io_cqring_timer_wakeup, clock_id,
-				       HRTIMER_MODE_ABS);
+				       mode);
 	}
 
 	hrtimer_set_expires_range_ns(&iowq->t, timeout, 0);
-	hrtimer_start_expires(&iowq->t, HRTIMER_MODE_ABS);
+	hrtimer_start_expires(&iowq->t, mode);
 
 	if (!READ_ONCE(iowq->hit_timeout))
 		schedule();