mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Mike Galbraith <efault@gmx.de>
To: Peter Zijlstra <peterz@infradead.org>
Cc: linux-kernel <linux-kernel@vger.kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	"Paul E. McKenney" <paulmck@us.ibm.com>,
	linux-rt-users <linux-rt-users@vger.kernel.org>
Subject: [patch] sched, rt: fix migrate_enable() thinko
Date: Tue, 23 Aug 2011 16:12:43 +0200	[thread overview]
Message-ID: <1314108763.6689.4.camel@marge.simson.net> (raw)
In-Reply-To: <1313232790.25267.7.camel@twins>


Assigning mask = tsk_cpus_allowed(p) after p->migrate_disable = 0 ensures
that we won't see a mask change.. no push/pull, we stack tasks on one CPU.

Also add a couple fields to sched_debug for the next guy.

Signed-off-by: Mike Galbraith <efault@gmx.de>

---
 kernel/sched.c       |    4 +++-
 kernel/sched_debug.c |    3 +++
 2 files changed, 6 insertions(+), 1 deletion(-)

Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -6375,12 +6375,14 @@ void migrate_enable(void)
 	 */
 	rq = this_rq();
 	raw_spin_lock_irqsave(&rq->lock, flags);
-	p->migrate_disable = 0;
 	mask = tsk_cpus_allowed(p);
+	p->migrate_disable = 0;
 
 	WARN_ON(!cpumask_test_cpu(smp_processor_id(), mask));
 
 	if (!cpumask_equal(&p->cpus_allowed, mask)) {
+		/* Get the mask now that migration is enabled */
+		mask = tsk_cpus_allowed(p);
 		if (p->sched_class->set_cpus_allowed)
 			p->sched_class->set_cpus_allowed(p, mask);
 		p->rt.nr_cpus_allowed = cpumask_weight(mask);
Index: linux-2.6/kernel/sched_debug.c
===================================================================
--- linux-2.6.orig/kernel/sched_debug.c
+++ linux-2.6/kernel/sched_debug.c
@@ -235,6 +235,7 @@ void print_rt_rq(struct seq_file *m, int
 	P(rt_throttled);
 	PN(rt_time);
 	PN(rt_runtime);
+	P(rt_nr_migratory);
 
 #undef PN
 #undef P
@@ -484,6 +485,8 @@ void proc_sched_show_task(struct task_st
 	P(se.load.weight);
 	P(policy);
 	P(prio);
+	P(migrate_disable);
+	P(rt.nr_cpus_allowed);
 #undef PN
 #undef __PN
 #undef P



  parent reply	other threads:[~2011-08-23 14:13 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-08-13 10:53 [ANNOUNCE] 3.0.1-rt11 Peter Zijlstra
2011-08-13 11:48 ` Mike Galbraith
2011-08-13 11:58   ` Peter Zijlstra
2011-08-13 13:59     ` Mike Galbraith
2011-08-13 14:23       ` Peter Zijlstra
2011-08-13 16:27       ` Paul E. McKenney
2011-08-14  4:23         ` Mike Galbraith
2011-08-16 14:17           ` Nivedita Singhvi
2011-08-16 15:10             ` Mike Galbraith
2011-08-16 15:18               ` Nivedita Singhvi
2011-08-16 19:31               ` Paul E. McKenney
2011-08-17  4:28                 ` Mike Galbraith
2011-08-17  5:03                   ` Nivedita Singhvi
2011-08-15 10:09         ` Mike Galbraith
2011-08-14 21:19 ` Clark Williams
2011-08-23 14:12 ` Mike Galbraith [this message]
2011-09-08  2:11   ` [patch] sched, rt: fix migrate_enable() thinko Frank Rowand
2011-09-08  4:58     ` Mike Galbraith
2011-08-24 23:58 ` [ANNOUNCE] 3.0.1-rt11 Frank Rowand
2011-08-26 23:55   ` Paul E. McKenney
2011-08-29 19:57     ` Frank Rowand
2011-08-30  3:17       ` Paul E. McKenney
2011-09-07  2:53     ` Frank Rowand
2011-09-07  3:00       ` Frank Rowand
2011-09-07  6:42       ` Paul E. McKenney
2011-09-07  9:25       ` Thomas Gleixner
2011-09-07 10:46         ` Russell King - ARM Linux
2011-09-07 10:47           ` Russell King - ARM Linux
2011-09-07 10:57             ` Thomas Gleixner
2011-09-07 14:01               ` Russell King - ARM Linux
2011-09-07 16:32                 ` Thomas Gleixner
2011-09-07 16:33                 ` Frank Rowand

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=1314108763.6689.4.camel@marge.simson.net \
    --to=efault@gmx.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rt-users@vger.kernel.org \
    --cc=paulmck@us.ibm.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome