All of lore.kernel.org
 help / color / mirror / Atom feed
From: sashiko-bot@kernel.org
To: "Mathieu Desnoyers" <mathieu.desnoyers@efficios.com>
Cc: linux-rt-devel@lists.linux.dev, tj@kernel.org,
	hannes@cmpxchg.org, mkoutny@suse.com,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH v10 38/40] sched/deadline: Boost an owner that cannot run on its own reservation
Date: Fri, 20 Nov 2026 21:33:27 +0000	[thread overview]
Message-ID: <sashiko-outbox-226195@kernel.org> (raw)
In-Reply-To: <297755d1d8dde37f65e12a4cd502c6332011f44c.1795207233.git.mathieu.desnoyers@efficios.com>

Thank you for your contribution! Sashiko AI review found 6 potential
issues to consider:
- [High] sched/deadline: missing throttle restoration in dl_deboost()
- [High] sched/deadline: donor period added to own_deadline in
  replenish_dl_entity()
- [Medium] sched/deadline: missing dl_boost_held check in
  switched_from_dl()
- [Medium] sched/deadline: expired own_deadline restored in dl_deboost()
- [Medium] sched/deadline: stale deadline on PI chain in
  dl_boost_blocked()
- [Medium] sched/deadline: missing refill on boosted wakeup in
  enqueue_task_dl()
--

commit 59eba5619dd87ca592a528ffc0286ed100abcecc
Author: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

sched/deadline: Boost an owner that cannot run on its own reservation

This commit updates deadline priority inheritance so that a deadline
waiter boosts a lock owner that is throttled or past its deadline, saving
and restoring the owner's parameters across the boost when it could not
run on its own reservation.

> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 0dce129b41468..cbe0dfe26de3d 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -7974,10 +7974,13 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
>  			if (!dl_prio(p->normal_prio) ||
>  			    (pi_task && dl_prio(pi_task->prio) &&
>  			     !(p->dl.dl_new_params && p->dl.pi_se != &p->dl) &&
> -			     dl_entity_preempt(&pi_task->dl, &p->dl))) {
> +			     dl_waiter_boosts(p, pi_task))) {
>  				struct sched_dl_entity *old_donor = p->dl.pi_se;
>  
>  				dl_set_donor(&p->dl, pi_task);
> +				if (dl_prio(p->normal_prio) && old_donor == &p->dl &&
> +				    p->dl.pi_se != &p->dl)
> +					dl_boost_start(&p->dl);
>  				scope->flags |= ENQUEUE_REPLENISH;
>  				if (!scope->queued && p->dl.pi_se != old_donor)
>  					dl_boost_blocked(p);

[Severity: Medium]
When p is a deadline task blocked on another rt_mutex (!scope->queued),
does dl_boost_blocked(p) leave p->dl.deadline stale for the rest of the PI
chain walk?

sched_change_end() skips enqueue_task_dl() when !scope->queued, and
dl_boost_blocked() only replenishes tasks with !dl_se->dl_deadline &&
!dl_se->dl_throttled:

kernel/sched/deadline.c:dl_boost_blocked() {
	struct sched_dl_entity *dl_se = &p->dl;

	if (!dl_se->dl_deadline && !dl_se->dl_throttled &&
	    dl_task_pi_blocked(p))
		replenish_dl_new_period(dl_se, task_rq(p));
}

When p has its own deadline parameters or is throttled, p->dl.deadline is
not updated to the donor's deadline before rt_mutex_adjust_prio_chain()
calls waiter_update_prio() and dl_waiter_boosts() on the next lock in the
chain, so the boost fails to propagate across nested rt_mutexes.

> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index e9b3d3ec71d77..ff1c104f6afd8 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -161,21 +165,32 @@ static inline bool dl_task_pi_blocked(struct task_struct *p)
>  void dl_deboost(struct sched_dl_entity *dl_se)
>  {
>  	struct task_struct *p = dl_task_of(dl_se);
> -
> +	bool own = false;
> +
> +	/* Put back what dl_boost_start() saved. */
> +	if (dl_se->dl_boost_held) {
> +		dl_se->deadline = dl_se->own_deadline;
> +		dl_se->runtime = dl_se->own_runtime;
> +		dl_se->period_start = dl_se->own_period_start;
> +		dl_se->dl_donor_refill = 0;
> +		own = true;
> +	}

[Severity: High]
When a task that was boosted while throttled (own_runtime <= 0) is
deboosted before own_deadline, does restoring own_runtime without restoring
dl_throttled leave the task runnable on dl_rq with exhausted runtime?

When the boost started, enqueue_task_dl() canceled dl_timer and cleared
dl_se->dl_throttled = 0.  If the boost ends before own_deadline,
dl_deboost() restores own_deadline and own_runtime <= 0 with dl_throttled
still 0, and enqueue_dl_entity() only checks dl_check_constrained_dl() for
past deadlines before calling __enqueue_dl_entity(dl_se).  The exhausted
owner is then enqueued as runnable with its earlier own_deadline,
preventing the woken waiter from preempting it and running beyond its CBS
budget until the next tick.  If dl_new_params was set during the boost,
the subsequent dl_waiter_boosts() and dl_boost_start() check in
rt_mutex_setprio() also sees dl_throttled == 0 and misses that the owner
cannot run on its own reservation.

[Severity: Medium]
Should switched_from_dl() also restore own_deadline, own_runtime and
own_period_start when dl_boost_held is set?

If a task boosted with dl_boost_held changes policy to a non-deadline
class while boosted and leaves dl_sched_class at deboost,
rt_mutex_setprio() runs switched_from_dl() and dl_drop_boost() instead of
dl_deboost():

kernel/sched/deadline.c:switched_from_dl() {
	bool own_period = p->dl.dl_runtime && p->dl.dl_donor_refill;
    ...
	if (own_period)
		dl_start_own_period(&p->dl);

	if (task_on_rq_queued(p) && p->dl.dl_runtime)
		task_non_contending(&p->dl, false);
}

Because dl_donor_refill was set when the boosted task replenished from its
donor, switched_from_dl() calls dl_start_own_period() and resets runtime
to full dl_runtime instead of restoring the exhausted own_* reservation.
task_non_contending() then sees a 0-lag time of now and releases the
task's root-domain bandwidth immediately instead of waiting until the true
0-lag time of the saved period.

[ ... ]

> @@ -214,6 +229,62 @@ void dl_check_blocked_params(struct task_struct *p)
>  		update_dl_entity(dl_se);
>  	}
>  }
> +
> +/*
> + * Return true if the deadline waiter @pi_task must boost the owner @p,
> + * which has a deadline policy of its own. Compare @pi_task with the
> + * deadline that @p would run on:
> + * - @p is throttled, or past its deadline and before its next period:
> + *   it cannot run on its own reservation. Boost it.
> + * - @p was boosted for that reason: keep the boost until its own next
> + *   period. After that period starts, compare with now + dl_deadline.
> + * - @p is past its deadline otherwise: its next enqueue starts a new
> + *   period. Compare with now + dl_deadline.
> + * - Else, compare with the deadline of @p.
> + * A special entity, such as a sugov kthread, always boosts @p.
> + *
> + * The caller holds the rq lock of @p and has updated the rq clock.
> + */
> +bool dl_waiter_boosts(struct task_struct *p, struct task_struct *pi_task)
> +{
> +	struct sched_dl_entity *dl_se = &p->dl;
> +	u64 now = rq_clock(task_rq(p));
> +
> +	if (dl_entity_is_special(&pi_task->dl))
> +		return true;
> +	if (dl_se->dl_boost_held) {
> +		if (dl_time_before(now, dl_se->own_period_start + dl_se->dl_period))
> +			return true;
> +		return dl_time_before(pi_task->dl.deadline, now + dl_se->dl_deadline);
> +	}

[Severity: Medium]
Once now reaches own_period_start + dl_period, dl_waiter_boosts() compares
pi_task against now + dl_se->dl_deadline, but if it returns false and
triggers a deboost while p is pi-blocked on another rt_mutex, does
dl_deboost() restore the expired own_deadline instead of starting a new
period?

In dl_deboost(), the dl_boost_held branch unconditionally restores
dl_se->deadline = dl_se->own_deadline (which is now in the past) and
clears dl_se->dl_donor_refill = 0 so dl_start_own_period() is skipped.
When p is blocked on a second rt_mutex (!scope->queued), enqueue_task_dl()
does not run in sched_change_end(), so rt_mutex_adjust_prio_chain() copies
that expired past deadline into p's waiter node on the outer lock and
orders p ahead of waiters with valid future deadlines.  The same expired
own_deadline is also exposed on the outer lock if p is deboosted while
still in the constrained gap and pi-blocked.

> +	if (!is_dl_boosted(dl_se)) {
> +		if (dl_se->dl_throttled || dl_in_constrained_gap(dl_se))
> +			return true;
> +		if (dl_time_before(dl_se->deadline, now))
> +			return dl_time_before(pi_task->dl.deadline,
> +					      now + dl_se->dl_deadline);
> +	}
> +	return dl_entity_preempt(&pi_task->dl, dl_se);
> +}
> +
> +/*
> + * Call this when @dl_se gets its first donor, after dl_set_donor()
> + * installed it. If @dl_se cannot run on its own reservation, save its
> + * deadline, runtime and period start in own_*. Then set dl_boost_held.
> + * dl_deboost() puts them back. A task with no parameters of its own has
> + * nothing to save. The caller holds the rq lock and has updated the rq
> + * clock.
> + */
> +void dl_boost_start(struct sched_dl_entity *dl_se)
> +{
> +	if (!dl_se->dl_runtime ||
> +	    (!dl_se->dl_throttled && !dl_in_constrained_gap(dl_se)))
> +		return;
> +	dl_se->own_deadline = dl_se->deadline;
> +	dl_se->own_runtime = dl_se->runtime;
> +	dl_se->own_period_start = dl_se->period_start;
> +	dl_se->dl_boost_held = 1;
> +}

[Severity: Medium]
If an owner is throttled while going to sleep, boosted while asleep, and
then wakes up before own_deadline while still boosted, does
enqueue_task_dl() fail to replenish it from the donor?

When the boost happens while !scope->queued, ENQUEUE_REPLENISH is not
consumed by sched_change_end().  On the subsequent wakeup,
enqueue_task_dl(rq, p, ENQUEUE_WAKEUP) cancels dl_timer and clears
dl_se->dl_throttled = 0 without setting ENQUEUE_REPLENISH, so
enqueue_dl_entity() calls update_dl_entity(dl_se):

kernel/sched/deadline.c:update_dl_entity() {
    ...
	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
	    dl_entity_overflow(dl_se, rq_clock(rq))) {
    ...
		replenish_dl_new_period(dl_se, rq);
	}
}

Because rq_clock(rq) < own_deadline and dl_se->runtime <= 0 makes left <= 0
while right > 0 in dl_entity_overflow(), both checks are false and
replenish_dl_new_period() is skipped, enqueuing the boosted owner with
runtime <= 0 and its old own_deadline instead of the donor's parameters.

[ ... ]

> @@ -1443,7 +1514,13 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
>  	 * entity.
>  	 */
>  	if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
> -		printk_deferred_once("sched: DL replenish lagged too much\n");
> +		/*
> +		 * dl_waiter_boosts() boosts an owner past its deadline. Its
> +		 * deadline is then expected to be in the past: do not warn.
> +		 * The new period takes the donor's parameters.
> +		 */
> +		if (!is_dl_boosted(dl_se))
> +			printk_deferred_once("sched: DL replenish lagged too much\n");
>  		replenish_dl_new_period(dl_se, rq);
>  	}

[Severity: High]
When a runnable throttled owner (runtime <= 0) is boosted, does the
while (dl_se->runtime <= 0) loop right above this check advance
dl_se->deadline from own_deadline by the donor's period instead of
starting a donor period at rq_clock(rq)?

kernel/sched/deadline.c:replenish_dl_entity() {
    ...
	while (dl_se->runtime <= 0) {
		dl_se->deadline += period;
		dl_se->period_start += period;
		dl_se->runtime += runtime;
	}

	if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
		if (!is_dl_boosted(dl_se))
			printk_deferred_once("sched: DL replenish lagged too much\n");
		replenish_dl_new_period(dl_se, rq);
	}
}

For any throttled owner whose own_deadline has not passed yet (or is
within one donor period of rq_clock(rq)), adding the donor's period to
own_deadline keeps dl_se->deadline >= rq_clock(rq), so
replenish_dl_new_period() is never reached.  The boosted owner runs with a
deadline of own_deadline + pi_se->dl_period (later than its unboosted
own_deadline) instead of rq_clock(rq) + pi_se->dl_deadline, and its own
pre-boost overrun is deducted from the donor's runtime while also being
restored from own_runtime at dl_deboost().

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1795207232.git.mathieu.desnoyers@efficios.com?part=38

  reply	other threads:[~2026-11-20 21:33 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-20 20:41 [PATCH v10 00/40] sched/deadline: bandwidth accounting fixes and selftests Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 01/40] sched/deadline: Keep departing bandwidth across a root domain rebuild Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 02/40] sched/deadline: Rebuild the root domains' accounting from the task list Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 03/40] sched/deadline: Record the root domain holding a task's bandwidth Mathieu Desnoyers
2026-11-20 21:18   ` sashiko-bot
2026-11-20 20:41 ` [PATCH v10 04/40] sched/deadline: Leave a dying task out of a rebuild of the accounting Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 05/40] selftests/sched: Test SCHED_DEADLINE bandwidth across a root domain rebuild Mathieu Desnoyers
2026-11-20 21:12   ` sashiko-bot
2026-11-20 20:41 ` [PATCH v10 06/40] selftests/sched: Test the root domain rebuild in deadline_bw_test Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 07/40] sched/deadline: Move a task's bandwidth only where room was made Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 08/40] cgroup/cpuset: Wait for an attach before rebuilding the sched domains Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 09/40] sched: Make deadline policy and affinity changes wait for a cpuset attach Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 10/40] cgroup/cpuset: Give back the bandwidth an attach did not move Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 11/40] cgroup/cpuset: Reserve the bandwidth in the root domain a task moves to Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 12/40] selftests/sched: Test cpuset moves in deadline_bw_test Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 13/40] sched/deadline: Make a rebuild count a task in the root domain it runs in Mathieu Desnoyers
2026-11-20 21:11   ` sashiko-bot
2026-11-20 20:41 ` [PATCH v10 14/40] sched/deadline: Move a task's bandwidth to " Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 15/40] sched/deadline: Keep a task in the root domain that counts its bandwidth Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 16/40] sched/deadline: Keep the last CPU a task has in its root domain Mathieu Desnoyers
2026-11-20 21:19   ` sashiko-bot
2026-11-20 20:41 ` [PATCH v10 17/40] cgroup/cpuset: Refuse to take a deadline task out of " Mathieu Desnoyers
2026-11-20 21:22   ` sashiko-bot
2026-11-20 20:41 ` [PATCH v10 18/40] selftests/sched: Test the root domain of a task in deadline_bw_test Mathieu Desnoyers
2026-11-20 20:54   ` sashiko-bot
2026-11-20 20:41 ` [PATCH v10 19/40] sched/deadline: Count only active CPUs when spreading extra_bw Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 20/40] sched/deadline: Do not truncate a bandwidth to 32 bits in __dl_add/sub() Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 21/40] rtmutex: Continue the chain walk when a waiter's deadline donor changes Mathieu Desnoyers
2026-11-20 20:41 ` [PATCH v10 22/40] rtmutex: Do not stop the chain walk at an owner whose top waiter changed Mathieu Desnoyers
2026-11-20 20:42 ` [PATCH v10 23/40] sched/deadline: Hold a reference on the deadline donor of a boosted task Mathieu Desnoyers
2026-11-20 20:42 ` [PATCH v10 24/40] selftests/sched: Test the rtmutex chain walk in deadline_bw_test Mathieu Desnoyers
2026-11-20 21:06   ` sashiko-bot
2026-11-20 20:42 ` [PATCH v10 25/40] sched/deadline: Reset the donor's runtime at a deboost in the class Mathieu Desnoyers
2026-11-20 21:26   ` sashiko-bot
2026-11-20 20:42 ` [PATCH v10 26/40] sched/deadline: Replenish a throttled task boosted while asleep Mathieu Desnoyers
2026-11-20 21:22   ` sashiko-bot
2026-11-20 20:42 ` [PATCH v10 27/40] sched/deadline: Count the bandwidth a boosted task is given Mathieu Desnoyers
2026-11-20 20:42 ` [PATCH v10 28/40] sched/deadline: Start a period for a task that enters the class blocked Mathieu Desnoyers
2026-11-20 21:21   ` sashiko-bot
2026-11-20 20:42 ` [PATCH v10 29/40] sched/deadline: Start a period at a deboost out of the class Mathieu Desnoyers
2026-11-20 20:42 ` [PATCH v10 30/40] sched/deadline: Start a period for a task requeued onto an rt_mutex Mathieu Desnoyers
2026-11-20 21:24   ` sashiko-bot
2026-11-20 20:42 ` [PATCH v10 31/40] selftests/sched: Test deadline boosts in deadline_bw_test Mathieu Desnoyers
2026-11-20 21:08   ` sashiko-bot
2026-11-20 20:42 ` [PATCH v10 32/40] sched/deadline: Cancel the replenishment timer with the parameters Mathieu Desnoyers
2026-11-20 20:42 ` [PATCH v10 33/40] sched/deadline: Cap the runtime left of a constrained task at dl_runtime Mathieu Desnoyers
2026-11-20 20:42 ` [PATCH v10 34/40] sched/deadline: Check the runtime of a task that comes back runnable Mathieu Desnoyers
2026-11-20 20:42 ` [PATCH v10 35/40] sched/deadline: Check the runtime of a task whose parameters change Mathieu Desnoyers
2026-11-20 21:38   ` sashiko-bot
2026-11-20 20:42 ` [PATCH v10 36/40] sched/deadline: Reschedule a running task throttled at its enqueue Mathieu Desnoyers
2026-11-20 20:42 ` [PATCH v10 37/40] sched/deadline: Keep the start of the period across a change of dl_deadline Mathieu Desnoyers
2026-11-20 21:21   ` sashiko-bot
2026-11-20 20:42 ` [PATCH v10 38/40] sched/deadline: Boost an owner that cannot run on its own reservation Mathieu Desnoyers
2026-11-20 21:33   ` sashiko-bot [this message]
2026-11-20 20:42 ` [PATCH v10 39/40] selftests/sched: Test parameter changes in deadline_bw_test Mathieu Desnoyers
2026-11-20 20:42 ` [PATCH v10 40/40] selftests/sched: Share the helpers of the deadline tests Mathieu Desnoyers
2026-11-20 21:15   ` sashiko-bot

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=sashiko-outbox-226195@kernel.org \
    --to=sashiko-bot@kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rt-devel@lists.linux.dev \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mkoutny@suse.com \
    --cc=sashiko-reviews@lists.linux.dev \
    --cc=tj@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.