From 1ee14e6c8cddeeb8a490d7b54cd9016e4bb900b4 Mon Sep 17 00:00:00 2001 From: Ben Segall Date: Wed, 16 Oct 2013 11:16:12 -0700 Subject: sched: Fix race on toggling cfs_bandwidth_used When we transition cfs_bandwidth_used to false, any currently throttled groups will incorrectly return false from cfs_rq_throttled. While tg_set_cfs_bandwidth will unthrottle them eventually, currently running code (including at least dequeue_task_fair and distribute_cfs_runtime) will cause errors. Fix this by turning off cfs_bandwidth_used only after unthrottling all cfs_rqs. Tested: toggle bandwidth back and forth on a loaded cgroup. Caused crashes in minutes without the patch, hasn't crashed with it. Signed-off-by: Ben Segall Signed-off-by: Peter Zijlstra Cc: pjt@google.com Link: http://lkml.kernel.org/r/20131016181611.22647.80365.stgit@sword-of-the-dawn.mtv.corp.google.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7c61f313521d..450a34b2a637 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7436,7 +7436,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) runtime_enabled = quota != RUNTIME_INF; runtime_was_enabled = cfs_b->quota != RUNTIME_INF; - account_cfs_bandwidth_used(runtime_enabled, runtime_was_enabled); + /* + * If we need to toggle cfs_bandwidth_used, off->on must occur + * before making related changes, and on->off must occur afterwards + */ + if (runtime_enabled && !runtime_was_enabled) + cfs_bandwidth_usage_inc(); raw_spin_lock_irq(&cfs_b->lock); cfs_b->period = ns_to_ktime(period); cfs_b->quota = quota; @@ -7462,6 +7467,8 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) unthrottle_cfs_rq(cfs_rq); raw_spin_unlock_irq(&rq->lock); } + if (runtime_was_enabled && !runtime_enabled) + cfs_bandwidth_usage_dec(); out_unlock: mutex_unlock(&cfs_constraints_mutex); -- cgit v1.2.2