Re: [PATCH] sched/debug: initialize sd_sysctl_cpus if !CONFIG_CPUMASK_OFFSTACK

[Peter Zijlstra]

On Tue, Jan 29, 2019 at 10:12:45AM -0500, Masayoshi Mizuma wrote:
> From: Hidetoshi Seto <seto.hideto...@jp.fujitsu.com>
> 
> register_sched_domain_sysctl() copies the cpu_possible_mask into
> sd_sysctl_cpus, but only if sd_sysctl_cpus hasn't already been
> allocated (ie, CONFIG_CPUMASK_OFFSTACK is set).  However, when
> CONFIG_CPUMASK_OFFSTACK is not set, sd_sysctl_cpus is left uninitialized
> (all zeroes) and the kernel may fail to initialize sched_domain sysctl
> entries for all possible cpus.
> 
> This is visible to the user if the kernel is booted with maxcpus=n, or
> if ACPI tables have been modified to leave cpus offline, and then
> checking for missing /proc/sys/kernel/sched_domain/cpu* entries.
> 
> Fix this by separating the allocataion and initialization, and adding
> a flag to initialize the possible cpu entries while system booting only.
> 
> Signed-off-by: Hidetoshi Seto <seto.hideto...@jp.fujitsu.com>
> Reviewed-by: Masayoshi Mizuma <m.miz...@jp.fujitsu.com>
> Tested-by: Syuuichirou Ishii <ishii.shuuic...@jp.fujitsu.com>
> Tested-by: Tarumizu, Kohei <tarumizu.ko...@jp.fujitsu.com>
> ---
>  kernel/sched/debug.c | 4 ++++
>  1 file changed, 4 insertions(+)
> 
> diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
> index de3de997e245..9c6637f3e21d 100644
> --- a/kernel/sched/debug.c
> +++ b/kernel/sched/debug.c
> @@ -310,6 +310,7 @@ static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu)
>  
>  static cpumask_var_t         sd_sysctl_cpus;
>  static struct ctl_table_header       *sd_sysctl_header;
> +static int register_sched_domain_sysctl_on_boot = 1;
>  
>  void register_sched_domain_sysctl(void)
>  {
> @@ -344,9 +345,12 @@ void register_sched_domain_sysctl(void)
>       if (!cpumask_available(sd_sysctl_cpus)) {
>               if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
>                       return;
> +     }
>  
> +     if (register_sched_domain_sysctl_on_boot) {
>               /* init to possible to not have holes in @cpu_entries */
>               cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);
> +             register_sched_domain_sysctl_on_boot = 0;
>       }
>  
>       for_each_cpu(i, sd_sysctl_cpus) {

I change it like the below. By keeping the initial value 0 it can go
into .bss instead of .data.

--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -315,6 +315,7 @@ void register_sched_domain_sysctl(void)
 {
        static struct ctl_table *cpu_entries;
        static struct ctl_table **cpu_idx;
+       static bool init_done = false;
        char buf[32];
        int i;
 
@@ -344,7 +345,10 @@ void register_sched_domain_sysctl(void)
        if (!cpumask_available(sd_sysctl_cpus)) {
                if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
                        return;
+       }
 
+       if (!init_done) {
+               init_done = true;
                /* init to possible to not have holes in @cpu_entries */
                cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);
        }