hrtimer: Use and report correct timerslack values for realtime tasks

commit ed4fb6d7ef68111bb539283561953e5c6e9a6e38 upstream.

The timerslack_ns setting is used to specify how much the hardware
timers should be delayed, to potentially dispatch multiple timers in a
single interrupt. This is a performance optimization. Timers of
realtime tasks (having a realtime scheduling policy) should not be
delayed.

This logic was inconsitently applied to the hrtimers, leading to delays
of realtime tasks which used timed waits for events (e.g. condition
variables). Due to the downstream override of the slack for rt tasks,
the procfs reported incorrect (non-zero) timerslack_ns values.

This is changed by setting the timer_slack_ns task attribute to 0 for
all tasks with a rt policy. By that, downstream users do not need to
specially handle rt tasks (w.r.t. the slack), and the procfs entry
shows the correct value of "0". Setting non-zero slack values (either
via procfs or PR_SET_TIMERSLACK) on tasks with a rt policy is ignored,
as stated in "man 2 PR_SET_TIMERSLACK":

  Timer slack is not applied to threads that are scheduled under a
  real-time scheduling policy (see sched_setscheduler(2)).

The special handling of timerslack on rt tasks in downstream users
is removed as well.

Signed-off-by: Felix Moessbauer <felix.moessbauer@siemens.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20240814121032.368444-2-felix.moessbauer@siemens.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 13 insertions, 15 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0a483fd9f5de..9be8a509b5f3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7380,6 +7380,14 @@ static void __setscheduler_params(struct task_struct *p,
 	else if (fair_policy(policy))
 		p->static_prio = NICE_TO_PRIO(attr->sched_nice);
 
+	/* rt-policy tasks do not have a timerslack */
+	if (task_is_realtime(p)) {
+		p->timer_slack_ns = 0;
+	} else if (p->timer_slack_ns == 0) {
+		/* when switching back to non-rt policy, restore timerslack */
+		p->timer_slack_ns = p->default_timer_slack_ns;
+	}
+
 	/*
 	 * __sched_setscheduler() ensures attr->sched_priority == 0 when
 	 * !rt_policy. Always setting this ensures that things like
diff --git a/kernel/sys.c b/kernel/sys.c
index d06eda1387b6..06a9a87a8d3e 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2477,6 +2477,8 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			error = current->timer_slack_ns;
 		break;
 	case PR_SET_TIMERSLACK:
+		if (task_is_realtime(current))
+			break;
 		if (arg2 <= 0)
 			current->timer_slack_ns =
 					current->default_timer_slack_ns;
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 8db65e2db14c..f6d799646dd9 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -2090,14 +2090,9 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode,
 	struct restart_block *restart;
 	struct hrtimer_sleeper t;
 	int ret = 0;
-	u64 slack;
-
-	slack = current->timer_slack_ns;
-	if (dl_task(current) || rt_task(current))
-		slack = 0;
 
 	hrtimer_init_sleeper_on_stack(&t, clockid, mode);
-	hrtimer_set_expires_range_ns(&t.timer, rqtp, slack);
+	hrtimer_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns);
 	ret = do_nanosleep(&t, mode);
 	if (ret != -ERESTART_RESTARTBLOCK)
 		goto out;
@@ -2278,7 +2273,7 @@ void __init hrtimers_init(void)
 /**
  * schedule_hrtimeout_range_clock - sleep until timeout
  * @expires:	timeout value (ktime_t)
- * @delta:	slack in expires timeout (ktime_t) for SCHED_OTHER tasks
+ * @delta:	slack in expires timeout (ktime_t)
  * @mode:	timer mode
  * @clock_id:	timer clock to be used
  */
@@ -2305,13 +2300,6 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
 		return -EINTR;
 	}
 
-	/*
-	 * Override any slack passed by the user if under
-	 * rt contraints.
-	 */
-	if (rt_task(current))
-		delta = 0;
-
 	hrtimer_init_sleeper_on_stack(&t, clock_id, mode);
 	hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
 	hrtimer_sleeper_start_expires(&t, mode);
@@ -2331,7 +2319,7 @@ EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock);
 /**
  * schedule_hrtimeout_range - sleep until timeout
  * @expires:	timeout value (ktime_t)
- * @delta:	slack in expires timeout (ktime_t) for SCHED_OTHER tasks
+ * @delta:	slack in expires timeout (ktime_t)
  * @mode:	timer mode
  *
  * Make the current task sleep until the given expiry time has