linux-kernel - [tip: sched/core] sched/deadline: Reduce rq lock contention in dl_add_task_root

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <161296521364.23325.3769071094517881031.tip-bot2@tip-bot2>
Date:   Wed, 10 Feb 2021 13:53:33 -0000
From:   "tip-bot2 for Dietmar Eggemann" <tip-bot2@...utronix.de>
To:     linux-tip-commits@...r.kernel.org
Cc:     Dietmar Eggemann <dietmar.eggemann@....com>,
        "Peter Zijlstra (Intel)" <peterz@...radead.org>,
        Quentin Perret <qperret@...gle.com>,
        Valentin Schneider <valentin.schneider@....com>,
        Daniel Bristot de Oliveira <bristot@...hat.com>,
        Juri Lelli <juri.lelli@...hat.com>, x86@...nel.org,
        linux-kernel@...r.kernel.org
Subject: [tip: sched/core] sched/deadline: Reduce rq lock contention in
 dl_add_task_root_domain()

The following commit has been merged into the sched/core branch of tip:

Commit-ID:     3096b6fe494b7b4e45d20cb77aa6b715a3efe344
Gitweb:        https://git.kernel.org/tip/3096b6fe494b7b4e45d20cb77aa6b715a3efe344
Author:        Dietmar Eggemann <dietmar.eggemann@....com>
AuthorDate:    Tue, 19 Jan 2021 09:35:42 +01:00
Committer:     Peter Zijlstra <peterz@...radead.org>
CommitterDate: Wed, 10 Feb 2021 14:44:48 +01:00

sched/deadline: Reduce rq lock contention in dl_add_task_root_domain()

dl_add_task_root_domain() is called during sched domain rebuild:

  rebuild_sched_domains_locked()
    partition_and_rebuild_sched_domains()
      rebuild_root_domains()
         for all top_cpuset descendants:
           update_tasks_root_domain()
             for all tasks of cpuset:
               dl_add_task_root_domain()

Change it so that only the task pi lock is taken to check if the task
has a SCHED_DEADLINE (DL) policy. In case that p is a DL task take the
rq lock as well to be able to safely de-reference root domain's DL
bandwidth structure.

Most of the tasks will have another policy (namely SCHED_NORMAL) and
can now bail without taking the rq lock.

One thing to note here: Even in case that there aren't any DL user
tasks, a slow frequency switching system with cpufreq gov schedutil has
a DL task (sugov) per frequency domain running which participates in DL
bandwidth management.

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@....com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Reviewed-by: Quentin Perret <qperret@...gle.com>
Reviewed-by: Valentin Schneider <valentin.schneider@....com>
Reviewed-by: Daniel Bristot de Oliveira <bristot@...hat.com>
Acked-by: Juri Lelli <juri.lelli@...hat.com>
Link: https://lkml.kernel.org/r/20210119083542.19856-1-dietmar.eggemann@arm.com
---
 kernel/sched/deadline.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 1508d12..6f37796 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2388,9 +2388,13 @@ void dl_add_task_root_domain(struct task_struct *p)
 	struct rq *rq;
 	struct dl_bw *dl_b;
 
-	rq = task_rq_lock(p, &rf);
-	if (!dl_task(p))
-		goto unlock;
+	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
+	if (!dl_task(p)) {
+		raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
+		return;
+	}
+
+	rq = __task_rq_lock(p, &rf);
 
 	dl_b = &rq->rd->dl_bw;
 	raw_spin_lock(&dl_b->lock);
@@ -2399,7 +2403,6 @@ void dl_add_task_root_domain(struct task_struct *p)
 
 	raw_spin_unlock(&dl_b->lock);
 
-unlock:
 	task_rq_unlock(rq, p, &rf);
 }