Re: [PATCH v4 04/20] cpumask: Introduce cpu_preferred_mask

[Yury Norov <yury.norov@gmail.com>]

On Wed, Jun 17, 2026 at 11:11:23PM +0530, Shrikanth Hegde wrote:
> This patch does
> - Declare and Define cpu_preferred_mask.
> - Get/Set helpers for it.
> 
> Values are set/clear by the scheduler by detecting the steal time values.
> 
> A CPU is set to preferred when it becomes active. Later it may be
> marked as non-preferred depending on steal time values with
> steal monitor being enabled.
> 
> Always maintain design construct of preferred is subset of active.
> i.e. preferred ⊆ active ⊆ online ⊆ present ⊆ possible
> 
> Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
> ---
> v3->v4:
> - Make preferred subser of active instead of online.

s/subser/subset

> 
>  include/linux/cpumask.h | 21 ++++++++++++++++++++-
>  kernel/cpu.c            | 14 ++++++++++++++
>  kernel/sched/core.c     |  5 +++++
>  3 files changed, 39 insertions(+), 1 deletion(-)
> 
> diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
> index 80211900f373..30ea64cc1656 100644
> --- a/include/linux/cpumask.h
> +++ b/include/linux/cpumask.h
> @@ -120,12 +120,20 @@ extern struct cpumask __cpu_enabled_mask;
>  extern struct cpumask __cpu_present_mask;
>  extern struct cpumask __cpu_active_mask;
>  extern struct cpumask __cpu_dying_mask;
> +
> +#ifdef CONFIG_PREFERRED_CPU
> +extern struct cpumask __cpu_preferred_mask;
> +#else
> +#define __cpu_preferred_mask __cpu_active_mask
> +#endif
> +
>  #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask)
>  #define cpu_online_mask   ((const struct cpumask *)&__cpu_online_mask)
>  #define cpu_enabled_mask   ((const struct cpumask *)&__cpu_enabled_mask)
>  #define cpu_present_mask  ((const struct cpumask *)&__cpu_present_mask)
>  #define cpu_active_mask   ((const struct cpumask *)&__cpu_active_mask)
>  #define cpu_dying_mask    ((const struct cpumask *)&__cpu_dying_mask)
> +#define cpu_preferred_mask ((const struct cpumask *)&__cpu_preferred_mask)
>  
>  extern atomic_t __num_online_cpus;
>  extern unsigned int __num_possible_cpus;
> @@ -1164,6 +1172,7 @@ void init_cpu_possible(const struct cpumask *src);
>  
>  void set_cpu_online(unsigned int cpu, bool online);
>  void set_cpu_possible(unsigned int cpu, bool possible);
> +void set_cpu_preferred(unsigned int cpu, bool preferred);
>  
>  /**
>   * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask *
> @@ -1256,7 +1265,12 @@ static __always_inline bool cpu_dying(unsigned int cpu)
>  	return cpumask_test_cpu(cpu, cpu_dying_mask);
>  }
>  
> -#else
> +static __always_inline bool cpu_preferred(unsigned int cpu)
> +{
> +	return cpumask_test_cpu(cpu, cpu_preferred_mask);
> +}
> +
> +#else	/* NR_CPUS <= 1 */
>  
>  #define num_online_cpus()	1U
>  #define num_possible_cpus()	1U
> @@ -1294,6 +1308,11 @@ static __always_inline bool cpu_dying(unsigned int cpu)
>  	return false;
>  }
>  
> +static __always_inline bool cpu_preferred(unsigned int cpu)
> +{
> +	return cpu == 0;
> +}
> +
>  #endif /* NR_CPUS > 1 */
>  
>  #define cpu_is_offline(cpu)	unlikely(!cpu_online(cpu))
> diff --git a/kernel/cpu.c b/kernel/cpu.c
> index bc4f7a9ba64e..c196ba5d8b2a 100644
> --- a/kernel/cpu.c
> +++ b/kernel/cpu.c
> @@ -3107,6 +3107,11 @@ EXPORT_SYMBOL(__cpu_dying_mask);
>  atomic_t __num_online_cpus __read_mostly;
>  EXPORT_SYMBOL(__num_online_cpus);
>  
> +#ifdef CONFIG_PREFERRED_CPU
> +struct cpumask __cpu_preferred_mask __read_mostly;
> +EXPORT_SYMBOL(__cpu_preferred_mask);
> +#endif
> +
>  void init_cpu_present(const struct cpumask *src)
>  {
>  	cpumask_copy(&__cpu_present_mask, src);
> @@ -3154,6 +3159,14 @@ void set_cpu_possible(unsigned int cpu, bool possible)
>  	}
>  }
>  
> +void set_cpu_preferred(unsigned int cpu, bool preferred)
> +{
> +	if (!IS_ENABLED(CONFIG_PREFERRED_CPU))
> +		return;
> +
> +	assign_cpu((cpu), &__cpu_preferred_mask, (preferred));
> +}

set_cpu_xxx() is a macro on purpose - it improves code generation
quite a lot. See 5c563ee90a22d. Can you keep set_cpu_preferred aligned
with the other set_cpu(), i.e. make it a macro?

> +
>  /*
>   * Activate the first processor.
>   */
> @@ -3164,6 +3177,7 @@ void __init boot_cpu_init(void)
>  	/* Mark the boot cpu "present", "online" etc for SMP and UP case */
>  	set_cpu_online(cpu, true);
>  	set_cpu_active(cpu, true);
> +	set_cpu_preferred(cpu, true);
>  	set_cpu_present(cpu, true);
>  	set_cpu_possible(cpu, true);
>  
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 2f4530eb543f..9e16946c9d62 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -8685,6 +8685,9 @@ int sched_cpu_activate(unsigned int cpu)
>  	 */
>  	sched_set_rq_online(rq, cpu);
>  
> +	/* preferred is subset of active and follows its state */
> +	set_cpu_preferred(cpu, true);

Did you put it at the end of the function on purpose? If yes, please
add a comment. If no, I'd prefer to have it immediately after
set_cpu_active().

> +
>  	return 0;
>  }
>  
> @@ -8698,6 +8701,8 @@ int sched_cpu_deactivate(unsigned int cpu)
>  	if (ret)
>  		return ret;
>  
> +	set_cpu_preferred(cpu, false);
> +
>  	/*
>  	 * Remove CPU from nohz.idle_cpus_mask to prevent participating in
>  	 * load balancing when not active
> -- 
> 2.47.3