linux-kernel - Re: [PATCH 1/2] sched/deadline: add per rq tracking of admitted bandwidth

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: <20160211171012.GS11415@e106622-lin>
Date:	Thu, 11 Feb 2016 17:10:12 +0000
From:	Juri Lelli <juri.lelli@....com>
To:	Steven Rostedt <rostedt@...dmis.org>
Cc:	luca abeni <luca.abeni@...tn.it>, linux-kernel@...r.kernel.org,
	peterz@...radead.org, mingo@...hat.com, vincent.guittot@...aro.org,
	wanpeng.li@...mail.com
Subject: Re: [PATCH 1/2] sched/deadline: add per rq tracking of admitted
 bandwidth

On 11/02/16 09:25, Steven Rostedt wrote:
> On Thu, 11 Feb 2016 14:05:45 +0100
> luca abeni <luca.abeni@...tn.it> wrote:
> 
>   
> > Well, I never used the rq utilization to re-build the root_domain
> > utilization (and I never played with root domains too much... :)...
> > So, I do not really know. Maybe the code should do:
> > 	raw_spin_lock(&rq->lock);
> > 	raw_spin_lock(&cpu_rq(cpu)->lock);
> 
> Of course you want to use double_rq_lock() here instead.
> 

Right. Is something like this completely out of question/broken?

I slighly tested it with Steve's test and I don't see the warning
anymore (sched_debug looks good as well); but my confidence is still
pretty low. :(

--->8---

>From 9713e12bc682ca364e62f9d69bcd44598c50a8a9 Mon Sep 17 00:00:00 2001
From: Juri Lelli <juri.lelli@....com>
Date: Thu, 11 Feb 2016 16:55:49 +0000
Subject: [PATCH] fixup! sched/deadline: add per rq tracking of admitted
 bandwidth

Signed-off-by: Juri Lelli <juri.lelli@....com>
---
 include/linux/init_task.h |  1 +
 include/linux/sched.h     |  1 +
 kernel/sched/core.c       |  5 ++++-
 kernel/sched/deadline.c   | 26 +++++++++++++++++++++++++-
 4 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index f2cb8d4..c582f9d 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -199,6 +199,7 @@ extern struct task_group root_task_group;
 	.policy		= SCHED_NORMAL,					\
 	.cpus_allowed	= CPU_MASK_ALL,					\
 	.nr_cpus_allowed= NR_CPUS,					\
+	.fallback_cpu	= -1,						\
 	.mm		= NULL,						\
 	.active_mm	= &init_mm,					\
 	.restart_block = {						\
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a10494a..a6fc95c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1401,6 +1401,7 @@ struct task_struct {
 	struct task_struct *last_wakee;
 
 	int wake_cpu;
+	int fallback_cpu;
 #endif
 	int on_rq;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7fb9246..4e4bc41 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1442,7 +1442,8 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 				continue;
 			if (!cpu_active(dest_cpu))
 				continue;
-			if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
+			if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) {
+				p->fallback_cpu = dest_cpu;
 				return dest_cpu;
 		}
 	}
@@ -1490,6 +1491,7 @@ out:
 		}
 	}
 
+	p->fallback_cpu = dest_cpu;
 	return dest_cpu;
 }
 
@@ -1954,6 +1956,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	if (task_cpu(p) != cpu) {
 		wake_flags |= WF_MIGRATED;
 		set_task_cpu(p, cpu);
+		p->fallback_cpu = -1;
 	}
 #endif /* CONFIG_SMP */
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 6368f43..1eccecf 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1043,6 +1043,21 @@ static void yield_task_dl(struct rq *rq)
 
 #ifdef CONFIG_SMP
 
+static void swap_task_ac_bw(struct task_struct *p,
+			    struct rq *from,
+			    struct rq *to)
+{
+	unsigned long flags;
+
+	lockdep_assert_held(&p->pi_lock);
+	local_irq_save(flags);
+	double_rq_lock(from, to);
+	__dl_sub_ac(from, p->dl.dl_bw);
+	__dl_add_ac(to, p->dl.dl_bw);
+	double_rq_unlock(from, to);
+	local_irq_restore(flags);
+}
+
 static int find_later_rq(struct task_struct *task);
 
 static int
@@ -1077,8 +1092,10 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 		if (target != -1 &&
 				(dl_time_before(p->dl.deadline,
 					cpu_rq(target)->dl.earliest_dl.curr) ||
-				(cpu_rq(target)->dl.dl_nr_running == 0)))
+				(cpu_rq(target)->dl.dl_nr_running == 0))) {
 			cpu = target;
+			swap_task_ac_bw(p, rq, cpu_rq(target));
+		}
 	}
 	rcu_read_unlock();
 
@@ -1807,6 +1824,12 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
 		switched_to_dl(rq, p);
 }
 
+static void migrate_task_rq_dl(struct task_struct *p)
+{
+	if (p->fallback_cpu != -1)
+		swap_task_ac_bw(p, task_rq(p), cpu_rq(p->fallback_cpu));
+}
+
 const struct sched_class dl_sched_class = {
 	.next			= &rt_sched_class,
 	.enqueue_task		= enqueue_task_dl,
@@ -1820,6 +1843,7 @@ const struct sched_class dl_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_dl,
+	.migrate_task_rq	= migrate_task_rq_dl,
 	.set_cpus_allowed       = set_cpus_allowed_dl,
 	.rq_online              = rq_online_dl,
 	.rq_offline             = rq_offline_dl,
-- 
2.7.0