Re: [PATCH v6 03/23] cpumask: Introduce cpu_preferred_mask

[Shrikanth Hegde <sshegde@linux.ibm.com>]

Hi Yury, Thanks for taking a look at the patches.

On 7/1/26 9:05 PM, Yury Norov wrote:
> On Wed, Jul 01, 2026 at 07:46:34PM +0530, Shrikanth Hegde wrote:
>> Provide cpu_preferred_mask infrastructure. Define get/set macros
>> which could be used to get/set CPU state as preferred.
>>
>> Values are set/clear by the new driver called steal_monitor.
>> It periodically samples the steal time and decides preferred CPU state.
>>
>> 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
>>
>> With PREFERRED_CPU=n, set is nop and get returns active state.
>>
>> Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
>> ---
>> v5->v6:
>> - Make it nop for PREFERRED_CPU=n
>> - Make it EXPORT_SYMBOL_GPL
>>
>>   include/linux/cpumask.h | 27 ++++++++++++++++++++++++++-
>>   kernel/cpu.c            |  6 ++++++
>>   kernel/sched/core.c     |  5 +++++
>>   3 files changed, 37 insertions(+), 1 deletion(-)
>>
>> diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
>> index d3cda0544954..c97271c063ce 100644
>> --- a/include/linux/cpumask.h
>> +++ b/include/linux/cpumask.h
>> @@ -122,12 +122,20 @@ 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 +1172,13 @@ void init_cpu_possible(const struct cpumask *src);
>>   #define set_cpu_active(cpu, active)	assign_cpu((cpu), &__cpu_active_mask, (active))
>>   #define set_cpu_dying(cpu, dying)	assign_cpu((cpu), &__cpu_dying_mask, (dying))
>>   
>> +#ifdef CONFIG_PREFERRED_CPU
>> +#define set_cpu_preferred(cpu, preferred) assign_cpu((cpu), &__cpu_preferred_mask, (preferred))
>> +#else
>> +/* Don't edit active state when the feature is off */
> 
> And that makes a random reader thinking like why in the world he mentions
> active state here?
> 
> Can you move this in commit message, or drop entirely?

Ok. I will drop it.

> 
>> +#define set_cpu_preferred(cpu, preferred) {}
>> +#endif
>> +
>>   void set_cpu_online(unsigned int cpu, bool online);
>>   void set_cpu_possible(unsigned int cpu, bool possible);
>>   
>> @@ -1258,7 +1273,12 @@ 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 */
> 
> NR_CPUS can't be less than 1, I guess.

Ah yes. It can't be 0 :-)
this can only be  /* NR_CPUS == 1 */.

Since that is self explanatory, I guess it is good to drop that
comment addition. I think i did it to abide by that #else comment style
which i saw elsewhere.

> 
>>   
>>   #define num_online_cpus()	1U
>>   #define num_possible_cpus()	1U
>> @@ -1296,6 +1316,11 @@ 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 b3c8553d7bd6..376d297a6292 100644
>> --- a/kernel/cpu.c
>> +++ b/kernel/cpu.c
>> @@ -3103,6 +3103,11 @@ 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_GPL(__cpu_preferred_mask);
>> +#endif
>> +
>>   void init_cpu_present(const struct cpumask *src)
>>   {
>>   	cpumask_copy(&__cpu_present_mask, src);
>> @@ -3160,6 +3165,7 @@ 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 2e7cde033a31..a45f7c308329 100644
>> --- a/kernel/sched/core.c
>> +++ b/kernel/sched/core.c
>> @@ -8690,6 +8690,9 @@ 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);
>> +
>>   	return 0;
>>   }
>>   
>> @@ -8703,6 +8706,8 @@ 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