Re: [PATCH v8 -tip 02/26] sched: Introduce sched_class::pick_task()

[Li, Aubrey]

On 2020/10/22 23:25, Joel Fernandes wrote:
> On Thu, Oct 22, 2020 at 12:59 AM Li, Aubrey <aubrey.li@xxxxxxxxxxxxxxx> wrote:
>>
>> On 2020/10/20 9:43, Joel Fernandes (Google) wrote:
>>> From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
>>>
>>> Because sched_class::pick_next_task() also implies
>>> sched_class::set_next_task() (and possibly put_prev_task() and
>>> newidle_balance) it is not state invariant. This makes it unsuitable
>>> for remote task selection.
>>>
>>> Tested-by: Julien Desfossez <jdesfossez@xxxxxxxxxxxxxxxx>
>>> Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
>>> Signed-off-by: Vineeth Remanan Pillai <vpillai@xxxxxxxxxxxxxxxx>
>>> Signed-off-by: Julien Desfossez <jdesfossez@xxxxxxxxxxxxxxxx>
>>> Signed-off-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
>>> ---
>>>  kernel/sched/deadline.c  | 16 ++++++++++++++--
>>>  kernel/sched/fair.c      | 32 +++++++++++++++++++++++++++++++-
>>>  kernel/sched/idle.c      |  8 ++++++++
>>>  kernel/sched/rt.c        | 14 ++++++++++++--
>>>  kernel/sched/sched.h     |  3 +++
>>>  kernel/sched/stop_task.c | 13 +++++++++++--
>>>  6 files changed, 79 insertions(+), 7 deletions(-)
>>>
>>> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
>>> index 814ec49502b1..0271a7848ab3 100644
>>> --- a/kernel/sched/deadline.c
>>> +++ b/kernel/sched/deadline.c
>>> @@ -1848,7 +1848,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
>>>       return rb_entry(left, struct sched_dl_entity, rb_node);
>>>  }
>>>
>>> -static struct task_struct *pick_next_task_dl(struct rq *rq)
>>> +static struct task_struct *pick_task_dl(struct rq *rq)
>>>  {
>>>       struct sched_dl_entity *dl_se;
>>>       struct dl_rq *dl_rq = &rq->dl;
>>> @@ -1860,7 +1860,18 @@ static struct task_struct *pick_next_task_dl(struct rq *rq)
>>>       dl_se = pick_next_dl_entity(rq, dl_rq);
>>>       BUG_ON(!dl_se);
>>>       p = dl_task_of(dl_se);
>>> -     set_next_task_dl(rq, p, true);
>>> +
>>> +     return p;
>>> +}
>>> +
>>> +static struct task_struct *pick_next_task_dl(struct rq *rq)
>>> +{
>>> +     struct task_struct *p;
>>> +
>>> +     p = pick_task_dl(rq);
>>> +     if (p)
>>> +             set_next_task_dl(rq, p, true);
>>> +
>>>       return p;
>>>  }
>>>
>>> @@ -2517,6 +2528,7 @@ const struct sched_class dl_sched_class
>>>
>>>  #ifdef CONFIG_SMP
>>>       .balance                = balance_dl,
>>> +     .pick_task              = pick_task_dl,
>>>       .select_task_rq         = select_task_rq_dl,
>>>       .migrate_task_rq        = migrate_task_rq_dl,
>>>       .set_cpus_allowed       = set_cpus_allowed_dl,
>>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>>> index dbd9368a959d..bd6aed63f5e3 100644
>>> --- a/kernel/sched/fair.c
>>> +++ b/kernel/sched/fair.c
>>> @@ -4450,7 +4450,7 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
>>>        * Avoid running the skip buddy, if running something else can
>>>        * be done without getting too unfair.
>>>        */
>>> -     if (cfs_rq->skip == se) {
>>> +     if (cfs_rq->skip && cfs_rq->skip == se) {
>>>               struct sched_entity *second;
>>>
>>>               if (se == curr) {
>>> @@ -6976,6 +6976,35 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
>>>               set_last_buddy(se);
>>>  }
>>>
>>> +#ifdef CONFIG_SMP
>>> +static struct task_struct *pick_task_fair(struct rq *rq)
>>> +{
>>> +     struct cfs_rq *cfs_rq = &rq->cfs;
>>> +     struct sched_entity *se;
>>> +
>>> +     if (!cfs_rq->nr_running)
>>> +             return NULL;
>>> +
>>> +     do {
>>> +             struct sched_entity *curr = cfs_rq->curr;
>>> +
>>> +             se = pick_next_entity(cfs_rq, NULL);
>>> +
>>> +             if (curr) {
>>> +                     if (se && curr->on_rq)
>>> +                             update_curr(cfs_rq);
>>> +
>>> +                     if (!se || entity_before(curr, se))
>>> +                             se = curr;
>>> +             }
>>> +
>>> +             cfs_rq = group_cfs_rq(se);
>>> +     } while (cfs_rq);
>>> ++
>>> +     return task_of(se);
>>> +}
>>> +#endif
>>
>> One of my machines hangs when I run uperf with only one message:
>> [  719.034962] BUG: kernel NULL pointer dereference, address: 0000000000000050
>>
>> Then I replicated the problem on my another machine(no serial console),
>> here is the stack by manual copy.
>>
>> Call Trace:
>>  pick_next_entity+0xb0/0x160
>>  pick_task_fair+0x4b/0x90
>>  __schedule+0x59b/0x12f0
>>  schedule_idle+0x1e/0x40
>>  do_idle+0x193/0x2d0
>>  cpu_startup_entry+0x19/0x20
>>  start_secondary+0x110/0x150
>>  secondary_startup_64_no_verify+0xa6/0xab
> 
> Interesting. Wondering if we screwed something up in the rebase.
> 
> Questions:
> 1. Does the issue happen if you just apply only up until this patch,
> or the entire series?

I applied the entire series and just find a related patch to report the
issue.

> 2. Do you see the issue in v7? Not much if at all has changed in this
> part of the code from v7 -> v8 but could be something in the newer
> kernel.
> 

IIRC, I can run uperf successfully on v7.
I'm on tip/master 2d3e8c9424c9 (origin/master) "Merge branch 'linus'."
Please let me know if this is a problem, or you have a repo I can pull
for testing.

> We tested this series after rebase heavily so it is indeed strange to
> see this so late.
Cc Hongyu - Maybe we can run the test cases in our hand before next release.

Thanks,
-Aubrey