Re: [PATCH RFC tip/core/rcu] Fix attempt to avoid offloading callbacks unless requested

[Pranith Kumar <bobby.prani@gmail.com>]

On 07/25/2014 07:36 PM, Paul E. McKenney wrote:
> [ Note: This applies on top of commit 187497fa5e9e (rcu: Allow for NULL
>     tick_nohz_full_mask when nohz_full= missing) in -tip
>     or -rcu.  To make this work on top of rcu/next, move the
>     call to rcu_organize_nocb_kthreads(rsp) to the end of the
>     for_each_rcu_flavor(rsp) loop in rcu_init_nohz(). ]
>
> Commit b58cc46c5f6b (rcu: Don't offload callbacks unless specifically
> requested) failed to adjust the callback lists of the CPUs that are
> known to be no-CBs CPUs only because they are also nohz_full= CPUs.
> This failure can result in callbacks that are posted during early boot
> getting stranded on nxtlist for CPUs whose no-CBs property becomes
> apparent late, and there can also be spurious warnings about offline
> CPUs posting callbacks.
>
> This commit fixes these problems by adding an early-boot rcu_init_nohz()
> that properly initializes the no-CBs CPUs.
>
> Note that kernels built with CONFIG_RCU_NOCB_CPU_ALL=y or with
> CONFIG_RCU_NOCB_CPU=n do not exhibit this bug.  Neither do kernels
> booted without the nohz_full= boot parameter.
>
> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

Please find two points below.

<snip>
>  #ifdef CONFIG_TREE_PREEMPT_RCU
> @@ -2451,6 +2424,66 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
>      trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty"));
>  }
>  
> +void rcu_init_nohz(void)
> +{
> +    int cpu;
> +    bool need_rcu_nocb_mask = true;
> +    struct rcu_state *rsp;
> +
> +#ifdef CONFIG_RCU_NOCB_CPU_NONE
> +    need_rcu_nocb_mask = false;
> +#endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */
> +
> +#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL)
> +    if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask))
> +        need_rcu_nocb_mask = true;
> +#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */
> +
> +    if (!have_rcu_nocb_mask && need_rcu_nocb_mask) {
> +        zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL);

Please check the return value unless you want to increase my commit count ;)

>
> +        have_rcu_nocb_mask = true;
> +    }
> +    if (!have_rcu_nocb_mask)
> +        return;
> +
> +#ifdef CONFIG_RCU_NOCB_CPU_ZERO
> +    pr_info("\tOffload RCU callbacks from CPU 0\n");
> +    cpumask_set_cpu(0, rcu_nocb_mask);
> +#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */
> +#ifdef CONFIG_RCU_NOCB_CPU_ALL
> +    pr_info("\tOffload RCU callbacks from all CPUs\n");
> +    cpumask_copy(rcu_nocb_mask, cpu_possible_mask);
> +#endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */
> +#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL)
> +    cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
> +#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */

I understand that if CONFIG_NO_HZ_FULL_ALL is set then CONFIG_NOCB_CPU_ALL
will also be set and there is no need for this cpumask_or().

Is there any reason for the coupling between CONFIG_NO_HZ_FULL_ALL
and CONFIG_NOCB_CPU_ALL?

I ask because a user can override CONFIG_NO_HZ_FULL_ALL=y at boot time
using the nohz_full= boot time parameter. In this case even if a user marks
CPU 0 as the only nohz_full cpu, we will offload call backs from all CPUs.
Is this behavior what you have in mind?

--
Pranith

>
> +
> +    if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
> +        pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n");
> +        cpumask_and(rcu_nocb_mask, cpu_possible_mask,
> +                rcu_nocb_mask);
> +    }
> +    cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);
> +    pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf);
> +    if (rcu_nocb_poll)
> +        pr_info("\tPoll for callbacks from no-CBs CPUs.\n");
> +
> +    for_each_rcu_flavor(rsp) {
> +        for_each_cpu(cpu, rcu_nocb_mask) {
> +            struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
> +
> +            /*
> +             * If there are early callbacks, they will need
> +             * to be moved to the nocb lists.
> +             */
> +            WARN_ON_ONCE(rdp->nxttail[RCU_NEXT_TAIL] !=
> +                     &rdp->nxtlist &&
> +                     rdp->nxttail[RCU_NEXT_TAIL] != NULL);
> +            init_nocb_callback_list(rdp);
> +        }
> +    }
> +}
> +
>  /* Initialize per-rcu_data variables for no-CBs CPUs. */
>  static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
>  {
> @@ -2479,10 +2512,6 @@ static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
>  
>      if (rcu_nocb_mask == NULL)
>          return;
> -#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL)
> -    if (tick_nohz_full_running)
> -        cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
> -#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */
>      if (ls == -1) {
>          ls = int_sqrt(nr_cpu_ids);
>          rcu_nocb_leader_stride = ls;
>