linux-kernel - [PATCH v2 1/3] sched/fair: Disable runtime

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 for Android: free password hash cracker in your pocket
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Date:	Tue, 24 Jun 2014 11:53:52 +0400
From:	Kirill Tkhai <ktkhai@...allels.com>
To:	<linux-kernel@...r.kernel.org>
CC:	Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...nel.org>, <tkhai@...dex.ru>,
	Srikar Dronamraju <srikar@...ux.vnet.ibm.com>,
	"Mike Galbraith" <umgwanakikbuti@...il.com>,
	<khorenko@...allels.com>, Ben Segall <bsegall@...gle.com>,
	Paul Turner <pjt@...gle.com>
Subject: [PATCH v2 1/3] sched/fair: Disable runtime_enabled on dying rq

We kill rq->rd on the CPU_DOWN_PREPARE stage:

	cpuset_cpu_inactive -> cpuset_update_active_cpus -> partition_sched_domains ->
	-> cpu_attach_domain -> rq_attach_root -> set_rq_offline

This unthrottles all throttled cfs_rqs.

But the cpu is still able to call schedule() till

	take_cpu_down->__cpu_disable()

is called from stop_machine.

This case the tasks from just unthrottled cfs_rqs are pickable
in a standard scheduler way, and they are picked by dying cpu.
The cfs_rqs becomes throttled again, and migrate_tasks()
in migration_call skips their tasks (one more unthrottle
in migrate_tasks()->CPU_DYING does not happen, because rq->rd
is already NULL).

Patch sets runtime_enabled to zero. This guarantees, the runtime
is not accounted, and the cfs_rqs won't exceed given
cfs_rq->runtime_remaining = 1, and tasks will be pickable
in migrate_tasks(). runtime_enabled is recalculated again
when rq becomes online again.

Ben Segall also noticed, we always enable runtime in
tg_set_cfs_bandwidth(). Actually, we should do that for online
cpus only. To fix that, we check if a cpu is online when
its rq is locked. This guarantees we do not have races with
set_rq_offline(), which also requires rq->lock.

v2: Fix race with tg_set_cfs_bandwidth().
    Move cfs_rq->runtime_enabled=0 above unthrottle_cfs_rq().

Signed-off-by: Kirill Tkhai <ktkhai@...allels.com>
CC: Konstantin Khorenko <khorenko@...allels.com>
CC: Ben Segall <bsegall@...gle.com>
CC: Paul Turner <pjt@...gle.com>
CC: Srikar Dronamraju <srikar@...ux.vnet.ibm.com>
CC: Mike Galbraith <umgwanakikbuti@...il.com>
CC: Peter Zijlstra <peterz@...radead.org>
CC: Ingo Molnar <mingo@...nel.org>
---
 kernel/sched/core.c |   15 +++++++++++----
 kernel/sched/fair.c |   22 ++++++++++++++++++++++
 2 files changed, 33 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7f3063c..707a3c5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7842,11 +7842,18 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 		struct rq *rq = cfs_rq->rq;
 
 		raw_spin_lock_irq(&rq->lock);
-		cfs_rq->runtime_enabled = runtime_enabled;
-		cfs_rq->runtime_remaining = 0;
+		/*
+		 * Do not enable runtime on offline runqueues. We specially
+		 * make it disabled in unthrottle_offline_cfs_rqs().
+		 */
+		if (cpu_online(i)) {
+			cfs_rq->runtime_enabled = runtime_enabled;
+			cfs_rq->runtime_remaining = 0;
+
+			if (cfs_rq->throttled)
+				unthrottle_cfs_rq(cfs_rq);
+		}
 
-		if (cfs_rq->throttled)
-			unthrottle_cfs_rq(cfs_rq);
 		raw_spin_unlock_irq(&rq->lock);
 	}
 	if (runtime_was_enabled && !runtime_enabled)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1f9c457..5616d23 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3776,6 +3776,19 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	hrtimer_cancel(&cfs_b->slack_timer);
 }
 
+static void __maybe_unused update_runtime_enabled(struct rq *rq)
+{
+	struct cfs_rq *cfs_rq;
+
+	for_each_leaf_cfs_rq(rq, cfs_rq) {
+		struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth;
+
+		raw_spin_lock(&cfs_b->lock);
+		cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF;
+		raw_spin_unlock(&cfs_b->lock);
+	}
+}
+
 static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 {
 	struct cfs_rq *cfs_rq;
@@ -3789,6 +3802,12 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 		 * there's some valid quota amount
 		 */
 		cfs_rq->runtime_remaining = 1;
+		/*
+		 * Offline rq is schedulable till cpu is completely disabled
+		 * in take_cpu_down(), so we prevent new cfs throttling here.
+		 */
+		cfs_rq->runtime_enabled = 0;
+
 		if (cfs_rq_throttled(cfs_rq))
 			unthrottle_cfs_rq(cfs_rq);
 	}
@@ -3832,6 +3851,7 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
 	return NULL;
 }
 static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
+static inline void update_runtime_enabled(struct rq *rq) {}
 static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
 
 #endif /* CONFIG_CFS_BANDWIDTH */
@@ -7325,6 +7345,8 @@ void trigger_load_balance(struct rq *rq)
 static void rq_online_fair(struct rq *rq)
 {
 	update_sysctl();
+
+	update_runtime_enabled(rq);
 }
 
 static void rq_offline_fair(struct rq *rq)



--
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/