[patch V2 09/20] cpumask: Cache num_possible_cpus()

Thomas Gleixner posted 20 patches 3 months, 2 weeks ago
There is a newer version of this series
[patch V2 09/20] cpumask: Cache num_possible_cpus()
Posted by Thomas Gleixner 3 months, 2 weeks ago
Reevaluating num_possible_cpus() over and over does not make sense. That
becomes a constant after init as cpu_possible_mask is marked ro_after_init.

Cache the value during initialization and provide that for consumption.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Yury Norov <yury.norov@gmail.com>
---
V2: New patch
---
 include/linux/cpumask.h |   10 ++++++++--
 kernel/cpu.c            |   15 +++++++++++++++
 2 files changed, 23 insertions(+), 2 deletions(-)

--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -126,6 +126,7 @@ extern struct cpumask __cpu_dying_mask;
 #define cpu_dying_mask    ((const struct cpumask *)&__cpu_dying_mask)
 
 extern atomic_t __num_online_cpus;
+extern unsigned int __num_possible_cpus;
 
 extern cpumask_t cpus_booted_once_mask;
 
@@ -1152,13 +1153,13 @@ void init_cpu_possible(const struct cpum
 #define __assign_cpu(cpu, mask, val)	\
 	__assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val))
 
-#define set_cpu_possible(cpu, possible)	assign_cpu((cpu), &__cpu_possible_mask, (possible))
 #define set_cpu_enabled(cpu, enabled)	assign_cpu((cpu), &__cpu_enabled_mask, (enabled))
 #define set_cpu_present(cpu, present)	assign_cpu((cpu), &__cpu_present_mask, (present))
 #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))
 
 void set_cpu_online(unsigned int cpu, bool online);
+void set_cpu_possible(unsigned int cpu, bool possible);
 
 /**
  * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask *
@@ -1211,7 +1212,12 @@ static __always_inline unsigned int num_
 {
 	return raw_atomic_read(&__num_online_cpus);
 }
-#define num_possible_cpus()	cpumask_weight(cpu_possible_mask)
+
+static __always_inline unsigned int num_possible_cpus(void)
+{
+	return __num_possible_cpus;
+}
+
 #define num_enabled_cpus()	cpumask_weight(cpu_enabled_mask)
 #define num_present_cpus()	cpumask_weight(cpu_present_mask)
 #define num_active_cpus()	cpumask_weight(cpu_active_mask)
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -3108,6 +3108,9 @@ EXPORT_SYMBOL(__cpu_dying_mask);
 atomic_t __num_online_cpus __read_mostly;
 EXPORT_SYMBOL(__num_online_cpus);
 
+unsigned int __num_possible_cpus __ro_after_init = NR_CPUS;
+EXPORT_SYMBOL(__num_possible_cpus);
+
 void init_cpu_present(const struct cpumask *src)
 {
 	cpumask_copy(&__cpu_present_mask, src);
@@ -3116,6 +3119,7 @@ void init_cpu_present(const struct cpuma
 void init_cpu_possible(const struct cpumask *src)
 {
 	cpumask_copy(&__cpu_possible_mask, src);
+	__num_possible_cpus = cpumask_weight(&__cpu_possible_mask);
 }
 
 void set_cpu_online(unsigned int cpu, bool online)
@@ -3139,6 +3143,17 @@ void set_cpu_online(unsigned int cpu, bo
 	}
 }
 
+void set_cpu_possible(unsigned int cpu, bool possible)
+{
+	if (possible) {
+		if (!cpumask_test_and_set_cpu(cpu, &__cpu_possible_mask))
+			__num_possible_cpus++;
+	} else {
+		if (cpumask_test_and_clear_cpu(cpu, &__cpu_possible_mask))
+			__num_possible_cpus--;
+	}
+}
+
 /*
  * Activate the first processor.
  */
Re: [patch V2 09/20] cpumask: Cache num_possible_cpus()
Posted by Yury Norov 3 months, 2 weeks ago
On Wed, Oct 22, 2025 at 02:55:30PM +0200, Thomas Gleixner wrote:
> Reevaluating num_possible_cpus() over and over does not make sense. That
> becomes a constant after init as cpu_possible_mask is marked ro_after_init.
> 
> Cache the value during initialization and provide that for consumption.
> 
> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
> Cc: Yury Norov <yury.norov@gmail.com>
> ---
> V2: New patch
> ---
>  include/linux/cpumask.h |   10 ++++++++--
>  kernel/cpu.c            |   15 +++++++++++++++
>  2 files changed, 23 insertions(+), 2 deletions(-)
> 
> --- a/include/linux/cpumask.h
> +++ b/include/linux/cpumask.h
> @@ -126,6 +126,7 @@ extern struct cpumask __cpu_dying_mask;
>  #define cpu_dying_mask    ((const struct cpumask *)&__cpu_dying_mask)
>  
>  extern atomic_t __num_online_cpus;
> +extern unsigned int __num_possible_cpus;
>  
>  extern cpumask_t cpus_booted_once_mask;
>  
> @@ -1152,13 +1153,13 @@ void init_cpu_possible(const struct cpum
>  #define __assign_cpu(cpu, mask, val)	\
>  	__assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val))
>  
> -#define set_cpu_possible(cpu, possible)	assign_cpu((cpu), &__cpu_possible_mask, (possible))
>  #define set_cpu_enabled(cpu, enabled)	assign_cpu((cpu), &__cpu_enabled_mask, (enabled))
>  #define set_cpu_present(cpu, present)	assign_cpu((cpu), &__cpu_present_mask, (present))
>  #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))
>  
>  void set_cpu_online(unsigned int cpu, bool online);
> +void set_cpu_possible(unsigned int cpu, bool possible);
>  
>  /**
>   * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask *
> @@ -1211,7 +1212,12 @@ static __always_inline unsigned int num_
>  {
>  	return raw_atomic_read(&__num_online_cpus);
>  }
> -#define num_possible_cpus()	cpumask_weight(cpu_possible_mask)
> +
> +static __always_inline unsigned int num_possible_cpus(void)
> +{
> +	return __num_possible_cpus;
> +}
> +
>  #define num_enabled_cpus()	cpumask_weight(cpu_enabled_mask)
>  #define num_present_cpus()	cpumask_weight(cpu_present_mask)
>  #define num_active_cpus()	cpumask_weight(cpu_active_mask)
> --- a/kernel/cpu.c
> +++ b/kernel/cpu.c
> @@ -3108,6 +3108,9 @@ EXPORT_SYMBOL(__cpu_dying_mask);
>  atomic_t __num_online_cpus __read_mostly;
>  EXPORT_SYMBOL(__num_online_cpus);
>  
> +unsigned int __num_possible_cpus __ro_after_init = NR_CPUS;
> +EXPORT_SYMBOL(__num_possible_cpus);
> +
>  void init_cpu_present(const struct cpumask *src)
>  {
>  	cpumask_copy(&__cpu_present_mask, src);
> @@ -3116,6 +3119,7 @@ void init_cpu_present(const struct cpuma
>  void init_cpu_possible(const struct cpumask *src)
>  {
>  	cpumask_copy(&__cpu_possible_mask, src);
> +	__num_possible_cpus = cpumask_weight(&__cpu_possible_mask);
>  }
>  
>  void set_cpu_online(unsigned int cpu, bool online)
> @@ -3139,6 +3143,17 @@ void set_cpu_online(unsigned int cpu, bo
>  	}
>  }
>  
> +void set_cpu_possible(unsigned int cpu, bool possible)
> +{
> +	if (possible) {
> +		if (!cpumask_test_and_set_cpu(cpu, &__cpu_possible_mask))
> +			__num_possible_cpus++;
> +	} else {
> +		if (cpumask_test_and_clear_cpu(cpu, &__cpu_possible_mask))
> +			__num_possible_cpus--;
> +	}
> +}

You can save a couple conditionals:

        if (possible)
                __num_possible_cpus += !cpumask_test_and_set_cpu(cpu, &__cpu_possible_mask));
        else
                __num_possible_cpus -= cpumask_test_and_clear_cpu(cpu, &__cpu_possible_mask));

Otherwise,

Reviewed-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>