Re: [PATCH Resend v5] sched: fix init NOHZ_IDLE flag

[Vincent Guittot]

On 4 April 2013 19:30, Vincent Guittot <vincent.guittot@xxxxxxxxxx> wrote:
> On 4 April 2013 19:07, Frederic Weisbecker <fweisbec@xxxxxxxxx> wrote:
>> 2013/4/3 Vincent Guittot <vincent.guittot@xxxxxxxxxx>:
>>> On my smp platform which is made of 5 cores in 2 clusters, I have the
>>> nr_busy_cpu field of sched_group_power struct that is not null when the
>>> platform is fully idle. The root cause is:
>>> During the boot sequence, some CPUs reach the idle loop and set their
>>> NOHZ_IDLE flag while waiting for others CPUs to boot. But the nr_busy_cpus
>>> field is initialized later with the assumption that all CPUs are in the busy
>>> state whereas some CPUs have already set their NOHZ_IDLE flag.
>>>
>>> More generally, the NOHZ_IDLE flag must be initialized when new sched_domains
>>> are created in order to ensure that NOHZ_IDLE and nr_busy_cpus are aligned.
>>>
>>> This condition can be ensured by adding a synchronize_rcu between the
>>> destruction of old sched_domains and the creation of new ones so the NOHZ_IDLE
>>> flag will not be updated with old sched_domain once it has been initialized.
>>> But this solution introduces a additionnal latency in the rebuild sequence
>>> that is called during cpu hotplug.
>>>
>>> As suggested by Frederic Weisbecker, another solution is to have the same
>>> rcu lifecycle for both NOHZ_IDLE and sched_domain struct. I have introduce
>>> a new sched_domain_rq struct that is the entry point for both sched_domains
>>> and objects that must follow the same lifecycle like NOHZ_IDLE flags. They
>>> will share the same RCU lifecycle and will be always synchronized.
>>>
>>> The synchronization is done at the cost of :
>>>  - an additional indirection for accessing the first sched_domain level
>>>  - an additional indirection and a rcu_dereference before accessing to the
>>>    NOHZ_IDLE flag.
>>>
>>> Change since v4:
>>>  - link both sched_domain and NOHZ_IDLE flag in one RCU object so
>>>    their states are always synchronized.
>>>
>>> Change since V3;
>>>  - NOHZ flag is not cleared if a NULL domain is attached to the CPU
>>>  - Remove patch 2/2 which becomes useless with latest modifications
>>>
>>> Change since V2:
>>>  - change the initialization to idle state instead of busy state so a CPU that
>>>    enters idle during the build of the sched_domain will not corrupt the
>>>    initialization state
>>>
>>> Change since V1:
>>>  - remove the patch for SCHED softirq on an idle core use case as it was
>>>    a side effect of the other use cases.
>>>
>>> Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
>>> ---
>>>  include/linux/sched.h |    6 +++
>>>  kernel/sched/core.c   |  105 ++++++++++++++++++++++++++++++++++++++++++++-----
>>>  kernel/sched/fair.c   |   35 +++++++++++------
>>>  kernel/sched/sched.h  |   24 +++++++++--
>>>  4 files changed, 145 insertions(+), 25 deletions(-)
>>>
>>> diff --git a/include/linux/sched.h b/include/linux/sched.h
>>> index d35d2b6..2a52188 100644
>>> --- a/include/linux/sched.h
>>> +++ b/include/linux/sched.h
>>> @@ -959,6 +959,12 @@ struct sched_domain {
>>>         unsigned long span[0];
>>>  };
>>>
>>> +struct sched_domain_rq {
>>> +       struct sched_domain *sd;
>>> +       unsigned long flags;
>>> +       struct rcu_head rcu;    /* used during destruction */
>>> +};
>>> +
>>>  static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
>>>  {
>>>         return to_cpumask(sd->span);
>>> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
>>> index 7f12624..69e2313 100644
>>> --- a/kernel/sched/core.c
>>> +++ b/kernel/sched/core.c
>>> @@ -5602,6 +5602,15 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu)
>>>                 destroy_sched_domain(sd, cpu);
>>>  }
>>>
>>> +static void destroy_sched_domain_rq(struct sched_domain_rq *sd_rq, int cpu)
>>> +{
>>> +       if (!sd_rq)
>>> +               return;
>>> +
>>> +       destroy_sched_domains(sd_rq->sd, cpu);
>>> +       kfree_rcu(sd_rq, rcu);
>>> +}
>>> +
>>>  /*
>>>   * Keep a special pointer to the highest sched_domain that has
>>>   * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
>>> @@ -5632,10 +5641,23 @@ static void update_top_cache_domain(int cpu)
>>>   * hold the hotplug lock.
>>>   */
>>>  static void
>>> -cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
>>> +cpu_attach_domain(struct sched_domain_rq *sd_rq, struct root_domain *rd,
>>> +               int cpu)
>>>  {
>>>         struct rq *rq = cpu_rq(cpu);
>>> -       struct sched_domain *tmp;
>>> +       struct sched_domain_rq *tmp_rq;
>>> +       struct sched_domain *tmp, *sd = NULL;
>>> +
>>> +       /*
>>> +        * If we don't have any sched_domain and associated object, we can
>>> +        * directly jump to the attach sequence otherwise we try to degenerate
>>> +        * the sched_domain
>>> +        */
>>> +       if (!sd_rq)
>>> +               goto attach;
>>> +
>>> +       /* Get a pointer to the 1st sched_domain */
>>> +       sd = sd_rq->sd;
>>>
>>>         /* Remove the sched domains which do not contribute to scheduling. */
>>>         for (tmp = sd; tmp; ) {
>>> @@ -5658,14 +5680,17 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
>>>                 destroy_sched_domain(tmp, cpu);
>>>                 if (sd)
>>>                         sd->child = NULL;
>>> +               /* update sched_domain_rq */
>>> +               sd_rq->sd = sd;
>>>         }
>>>
>>> +attach:
>>>         sched_domain_debug(sd, cpu);
>>>
>>>         rq_attach_root(rq, rd);
>>> -       tmp = rq->sd;
>>> -       rcu_assign_pointer(rq->sd, sd);
>>> -       destroy_sched_domains(tmp, cpu);
>>> +       tmp_rq = rq->sd_rq;
>>> +       rcu_assign_pointer(rq->sd_rq, sd_rq);
>>> +       destroy_sched_domain_rq(tmp_rq, cpu);
>>>
>>>         update_top_cache_domain(cpu);
>>>  }
>>> @@ -5695,12 +5720,14 @@ struct sd_data {
>>>  };
>>>
>>>  struct s_data {
>>> +       struct sched_domain_rq ** __percpu sd_rq;
>>>         struct sched_domain ** __percpu sd;
>>>         struct root_domain      *rd;
>>>  };
>>>
>>>  enum s_alloc {
>>>         sa_rootdomain,
>>> +       sa_sd_rq,
>>>         sa_sd,
>>>         sa_sd_storage,
>>>         sa_none,
>>> @@ -5935,7 +5962,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
>>>                 return;
>>>
>>>         update_group_power(sd, cpu);
>>> -       atomic_set(&sg->sgp->nr_busy_cpus, sg->group_weight);
>>> +       atomic_set(&sg->sgp->nr_busy_cpus, 0);
>>
>> Is it possible that we can be dealing here with a
>> sched_group/sched_group_power that is used on another CPU (from that
>> CPU's rq->rq_sd->sd) concurrently?
>> When we call build_sched_groups(), we might reuse an exisiting struct
>> sched_group used elsewhere right? If so, is there a race with the
>> above initialization?
>
> No we are not reusing an existing struct, the
> sched_group/sched_group_power that is initialized here, has just been
> created by __visit_domain_allocation_hell in build_sched_domains. The
> sched_group/sched_group_power is not already attached to any CPU
>

Hi Frederic,

Does it answer your concern and do you have more comments about the patch?

Vincent

> Vincent
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/