diff mbox series

[v3,4/4] sched/core: Avoid multiple calling update_rq_clock() in unthrottle_offline_cfs_rqs()

Message ID 20230515063848.77947-5-jiahao.os@bytedance.com
State New
Headers
Series Fix some warnings about rq clock |

Commit Message

Hao Jia May 15, 2023, 6:38 a.m. UTC 
  This WARN_DOUBLE_CLOCK warning is triggered during cpu offline.
------------[ cut here ]------------
rq->clock_update_flags & RQCF_UPDATED
WARNING: CPU: 0 PID: 3323 at kernel/sched/core.c:741
update_rq_clock+0xaf/0x180
Call Trace:
 <TASK>
 unthrottle_cfs_rq+0x4b/0x300
 rq_offline_fair+0x89/0x90
 set_rq_offline.part.118+0x28/0x60
 rq_attach_root+0xc4/0xd0
 cpu_attach_domain+0x3dc/0x7f0
 partition_sched_domains_locked+0x2a5/0x3c0
 rebuild_sched_domains_locked+0x477/0x830
 rebuild_sched_domains+0x1b/0x30
 cpuset_hotplug_workfn+0x2ca/0xc90
 ? balance_push+0x56/0xf0
 ? _raw_spin_unlock+0x15/0x30
 ? finish_task_switch+0x98/0x2f0
 ? __switch_to+0x291/0x410
 ? __schedule+0x65e/0x1310
 process_one_work+0x1bc/0x3d0
 worker_thread+0x4c/0x380
 ? preempt_count_add+0x92/0xa0
 ? rescuer_thread+0x310/0x310
 kthread+0xe6/0x110
 ? kthread_complete_and_exit+0x20/0x20
 ret_from_fork+0x1f/0x30

The rq clock has been updated before the set_rq_offline()
function runs, so we don't need to call update_rq_clock() in
unthrottle_offline_cfs_rqs().
We only need to call rq_clock_start_loop_update() before the
loop starts and rq_clock_stop_loop_update() after the loop
to avoid this warning.

Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Hao Jia <jiahao.os@bytedance.com>
---
 kernel/sched/fair.c | 9 +++++++++
 1 file changed, 9 insertions(+)

Comments

Vincent Guittot May 15, 2023, 1:30 p.m. UTC | #1 
On Mon, 15 May 2023 at 08:39, Hao Jia <jiahao.os@bytedance.com> wrote:
>
> This WARN_DOUBLE_CLOCK warning is triggered during cpu offline.
> ------------[ cut here ]------------
> rq->clock_update_flags & RQCF_UPDATED
> WARNING: CPU: 0 PID: 3323 at kernel/sched/core.c:741
> update_rq_clock+0xaf/0x180
> Call Trace:
>  <TASK>
>  unthrottle_cfs_rq+0x4b/0x300
>  rq_offline_fair+0x89/0x90
>  set_rq_offline.part.118+0x28/0x60
>  rq_attach_root+0xc4/0xd0
>  cpu_attach_domain+0x3dc/0x7f0
>  partition_sched_domains_locked+0x2a5/0x3c0
>  rebuild_sched_domains_locked+0x477/0x830
>  rebuild_sched_domains+0x1b/0x30
>  cpuset_hotplug_workfn+0x2ca/0xc90
>  ? balance_push+0x56/0xf0
>  ? _raw_spin_unlock+0x15/0x30
>  ? finish_task_switch+0x98/0x2f0
>  ? __switch_to+0x291/0x410
>  ? __schedule+0x65e/0x1310
>  process_one_work+0x1bc/0x3d0
>  worker_thread+0x4c/0x380
>  ? preempt_count_add+0x92/0xa0
>  ? rescuer_thread+0x310/0x310
>  kthread+0xe6/0x110
>  ? kthread_complete_and_exit+0x20/0x20
>  ret_from_fork+0x1f/0x30
>
> The rq clock has been updated before the set_rq_offline()
> function runs, so we don't need to call update_rq_clock() in
> unthrottle_offline_cfs_rqs().
> We only need to call rq_clock_start_loop_update() before the
> loop starts and rq_clock_stop_loop_update() after the loop
> to avoid this warning.
>
> Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
> Signed-off-by: Hao Jia <jiahao.os@bytedance.com>

Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>

> ---
>  kernel/sched/fair.c | 9 +++++++++
>  1 file changed, 9 insertions(+)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index af9604f4b135..9e961e0ec971 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -6124,6 +6124,13 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
>
>         lockdep_assert_rq_held(rq);
>
> +       /*
> +        * The rq clock has already been updated before the
> +        * set_rq_offline() runs, so we should skip updating
> +        * the rq clock again in unthrottle_cfs_rq().
> +        */
> +       rq_clock_start_loop_update(rq);
> +
>         rcu_read_lock();
>         list_for_each_entry_rcu(tg, &task_groups, list) {
>                 struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
> @@ -6146,6 +6153,8 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
>                         unthrottle_cfs_rq(cfs_rq);
>         }
>         rcu_read_unlock();
> +
> +       rq_clock_stop_loop_update(rq);
>  }
>
>  #else /* CONFIG_CFS_BANDWIDTH */
> --
> 2.37.0
>
diff mbox series

Patch

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index af9604f4b135..9e961e0ec971 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6124,6 +6124,13 @@  static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 
 	lockdep_assert_rq_held(rq);
 
+	/*
+	 * The rq clock has already been updated before the
+	 * set_rq_offline() runs, so we should skip updating
+	 * the rq clock again in unthrottle_cfs_rq().
+	 */
+	rq_clock_start_loop_update(rq);
+
 	rcu_read_lock();
 	list_for_each_entry_rcu(tg, &task_groups, list) {
 		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
@@ -6146,6 +6153,8 @@  static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 			unthrottle_cfs_rq(cfs_rq);
 	}
 	rcu_read_unlock();
+
+	rq_clock_stop_loop_update(rq);
 }
 
 #else /* CONFIG_CFS_BANDWIDTH */