linux-kernel - [RFC] sched: no preempt by RT task of throttled task group

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>] [day] [month] [year] [list]

Date:	Wed, 27 Jul 2011 21:24:08 +0800
From:	Hillf Danton <dhillf@...il.com>
To:	Paul Turner <pjt@...gle.com>
Cc:	LKML <linux-kernel@...r.kernel.org>,
	Steven Rostedt <rostedt@...dmis.org>,
	Vinod Koul <vinod.koul@...el.com>
Subject: [RFC] sched: no preempt by RT task of throttled task group

If the newly woken task is member of a throttled task group, the current task
should not be preempted, since the woken task is not eligible for schedule.

Would you please, Paul, give ideas on defining throttled task group, say

	task_group_throttled(task_group(task))

for a given RT task, since it is too hard to understand the teaching that
runqueue is never throttled but task group could.

Thanks,
Hillf
---
 kernel/sched_rt.c |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 97540f0..c6762eb 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1090,6 +1090,8 @@ static void check_preempt_equal_prio(struct rq
*rq, struct task_struct *p)
  */
 static void check_preempt_curr_rt(struct rq *rq, struct task_struct
*p, int flags)
 {
+	if (rt_rq_throttled(rt_rq_of_se(&p->rt)))
+		return;
 	if (p->prio < rq->curr->prio) {
 		resched_task(rq->curr);
 		return;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/