lkml.org 
[lkml]   [2014]   [May]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[PATCH] sched: tg_set_cfs_bandwidth() causes rq->lock deadlock
tg_set_cfs_bandwidth() sets cfs_b->timer_active to 0 to
force the period timer restart. It's not safe, because
can lead to deadlock, described in commit 927b54fccbf0:
"__start_cfs_bandwidth calls hrtimer_cancel while holding rq->lock,
waiting for the hrtimer to finish. However, if sched_cfs_period_timer
runs for another loop iteration, the hrtimer can attempt to take
rq->lock, resulting in deadlock."
If tg_set_cfs_bandwidth() resets cfs_b->timer_active concurrently
to the second iteration of sched_cfs_period_timer, deadlock occurs.

Instead of resetting cfs_b->timer_active, tg_set_cfs_bandwidth can
wait for period timer callbacks (ignoring cfs_b->timer_active) and
restart the timer explicitly.

Signed-off-by: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ben Segall <bsegall@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: pjt@google.com
Cc: Chris J Arges <chris.j.arges@canonical.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
kernel/sched/core.c | 3 +--
kernel/sched/fair.c | 8 ++++----
kernel/sched/sched.h | 2 +-
3 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d9d8ece..e9b9c66 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7717,8 +7717,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
/* restart the period timer (if active) to handle new period expiry */
if (runtime_enabled && cfs_b->timer_active) {
/* force a reprogram */
- cfs_b->timer_active = 0;
- __start_cfs_bandwidth(cfs_b);
+ __start_cfs_bandwidth(cfs_b, true);
}
raw_spin_unlock_irq(&cfs_b->lock);

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7570dd9..55a0a5b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3129,7 +3129,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
*/
if (!cfs_b->timer_active) {
__refill_cfs_bandwidth_runtime(cfs_b);
- __start_cfs_bandwidth(cfs_b);
+ __start_cfs_bandwidth(cfs_b, false);
}

if (cfs_b->runtime > 0) {
@@ -3308,7 +3308,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
raw_spin_lock(&cfs_b->lock);
list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
if (!cfs_b->timer_active)
- __start_cfs_bandwidth(cfs_b);
+ __start_cfs_bandwidth(cfs_b, false);
raw_spin_unlock(&cfs_b->lock);
}

@@ -3690,7 +3690,7 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
}

/* requires cfs_b->lock, may release to reprogram timer */
-void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
+void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force)
{
/*
* The timer may be active because we're trying to set a new bandwidth
@@ -3705,7 +3705,7 @@ void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
cpu_relax();
raw_spin_lock(&cfs_b->lock);
/* if someone else restarted the timer then we're done */
- if (cfs_b->timer_active)
+ if (!force && cfs_b->timer_active)
return;
}

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 456e492..369b4d6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -278,7 +278,7 @@ extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);

extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
-extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
+extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force);
extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);

extern void free_rt_sched_group(struct task_group *tg);
--
1.7.9.5


\
 
 \ /
  Last update: 2014-05-15 19:41    [W:0.222 / U:0.664 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site