summaryrefslogtreecommitdiffstats
path: root/kernel/sched/core.c
diff options
context:
space:
mode:
authorKirill Tkhai <ktkhai@parallels.com>2014-06-25 12:19:42 +0400
committerIngo Molnar <mingo@kernel.org>2014-07-05 11:17:42 +0200
commit0e59bdaea75f12a7d7c03672f4ac22c0119a1bc0 (patch)
treec0f74a1555354d622d64fb04b884c8a7f2bcb8d5 /kernel/sched/core.c
parenta22b4b012340b988dbe7a58461d6fcc582f34aa0 (diff)
downloadlinux-0e59bdaea75f12a7d7c03672f4ac22c0119a1bc0.tar.bz2
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 prevent races with unthrottle_offline_cfs_rqs() we take get_online_cpus() lock. Reviewed-by: Ben Segall <bsegall@google.com> Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Kirill Tkhai <ktkhai@parallels.com> CC: Konstantin Khorenko <khorenko@parallels.com> CC: Paul Turner <pjt@google.com> CC: Mike Galbraith <umgwanakikbuti@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1403684382.3462.42.camel@tkhai Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/sched/core.c')
-rw-r--r--kernel/sched/core.c8
1 files changed, 7 insertions, 1 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e50234ba0b27..2dbc63d1a847 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7817,6 +7817,11 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
if (period > max_cfs_quota_period)
return -EINVAL;
+ /*
+ * Prevent race between setting of cfs_rq->runtime_enabled and
+ * unthrottle_offline_cfs_rqs().
+ */
+ get_online_cpus();
mutex_lock(&cfs_constraints_mutex);
ret = __cfs_schedulable(tg, period, quota);
if (ret)
@@ -7842,7 +7847,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
}
raw_spin_unlock_irq(&cfs_b->lock);
- for_each_possible_cpu(i) {
+ for_each_online_cpu(i) {
struct cfs_rq *cfs_rq = tg->cfs_rq[i];
struct rq *rq = cfs_rq->rq;
@@ -7858,6 +7863,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
cfs_bandwidth_usage_dec();
out_unlock:
mutex_unlock(&cfs_constraints_mutex);
+ put_online_cpus();
return ret;
}