- cpumask_subset(a,b) -> cpumask_weight(a) should be same as 
cpumask_weight_and(a,b)

- for_each_cpu_and(a,b) to count cpus could be replaced by
cpumask_weight_and(a,b)

No Functional Change. It could save a few cycles since cpumask_weight_and 
would be more efficient. Plus one less stack variable. 

Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
---
 kernel/sched/deadline.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 8b7c4ee41fd8..a18f64b2e47c 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -125,20 +125,11 @@ static inline struct dl_bw *dl_bw_of(int i)
 static inline int dl_bw_cpus(int i)
 {
 	struct root_domain *rd = cpu_rq(i)->rd;
-	int cpus;
 
 	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
 			 "sched RCU must be held");
 
-	if (cpumask_subset(rd->span, cpu_active_mask))
-		return cpumask_weight(rd->span);
-
-	cpus = 0;
-
-	for_each_cpu_and(i, rd->span, cpu_active_mask)
-		cpus++;
-
-	return cpus;
+	return cpumask_weight_and(rd->span, cpu_active_mask);
 }
 
 static inline unsigned long __dl_bw_capacity(const struct cpumask *mask)
-- 
2.47.3

On Tue, Oct 14, 2025 at 03:33:42PM +0530, Shrikanth Hegde wrote:
> - cpumask_subset(a,b) -> cpumask_weight(a) should be same as 
> cpumask_weight_and(a,b)
> 
> - for_each_cpu_and(a,b) to count cpus could be replaced by
> cpumask_weight_and(a,b)
> 
> No Functional Change. It could save a few cycles since cpumask_weight_and 
> would be more efficient. Plus one less stack variable. 
> 
> Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
> ---
>  kernel/sched/deadline.c | 11 +----------
>  1 file changed, 1 insertion(+), 10 deletions(-)
> 
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index 8b7c4ee41fd8..a18f64b2e47c 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -125,20 +125,11 @@ static inline struct dl_bw *dl_bw_of(int i)
>  static inline int dl_bw_cpus(int i)
>  {
>  	struct root_domain *rd = cpu_rq(i)->rd;
> -	int cpus;
>  
>  	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
>  			 "sched RCU must be held");
>  
> -	if (cpumask_subset(rd->span, cpu_active_mask))
> -		return cpumask_weight(rd->span);
> -
> -	cpus = 0;
> -
> -	for_each_cpu_and(i, rd->span, cpu_active_mask)
> -		cpus++;
> -
> -	return cpus;
> +	return cpumask_weight_and(rd->span, cpu_active_mask);
>  }

Right, let me stick that on top of the change I have in queue/sched/core

The following commit has been merged into the sched/core branch of tip:

Commit-ID:     b4bfacd39216755c058f6d13c71c86a9bf5a1631
Gitweb:        https://git.kernel.org/tip/b4bfacd39216755c058f6d13c71c86a9bf5a1631
Author:        Shrikanth Hegde <sshegde@linux.ibm.com>
AuthorDate:    Tue, 14 Oct 2025 15:33:42 +05:30
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Tue, 11 Nov 2025 17:27:55 +01:00

sched/deadline: Use cpumask_weight_and() in dl_bw_cpus

cpumask_subset(a,b) -> cpumask_weight(a) should be same as cpumask_weight_and(a,b)
for_each_cpu_and(a,b) to count cpus could be replaced by cpumask_weight_and(a,b)

No Functional Change. It could save a few cycles since cpumask_weight_and
would be more efficient. Plus one less stack variable.

Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://patch.msgid.link/20251014100342.978936-3-sshegde@linux.ibm.com
---
 kernel/sched/deadline.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e958cf9..4dd4b2f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -125,20 +125,11 @@ static inline struct dl_bw *dl_bw_of(int i)
 static inline int dl_bw_cpus(int i)
 {
 	struct root_domain *rd = cpu_rq(i)->rd;
-	int cpus;
 
 	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
 			 "sched RCU must be held");
 
-	if (cpumask_subset(rd->span, cpu_active_mask))
-		return cpumask_weight(rd->span);
-
-	cpus = 0;
-
-	for_each_cpu_and(i, rd->span, cpu_active_mask)
-		cpus++;
-
-	return cpus;
+	return cpumask_weight_and(rd->span, cpu_active_mask);
 }
 
 static inline unsigned long __dl_bw_capacity(const struct cpumask *mask)

The following commit has been merged into the sched/core branch of tip:

Commit-ID:     7259e53915cc99298952a35aa8772d33d1e51866
Gitweb:        https://git.kernel.org/tip/7259e53915cc99298952a35aa8772d33d1e51866
Author:        Shrikanth Hegde <sshegde@linux.ibm.com>
AuthorDate:    Tue, 14 Oct 2025 15:33:42 +05:30
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Tue, 11 Nov 2025 12:33:39 +01:00

sched/deadline: Use cpumask_weight_and() in dl_bw_cpus

cpumask_subset(a,b) -> cpumask_weight(a) should be same as cpumask_weight_and(a,b)
for_each_cpu_and(a,b) to count cpus could be replaced by cpumask_weight_and(a,b)

No Functional Change. It could save a few cycles since cpumask_weight_and
would be more efficient. Plus one less stack variable.

Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://patch.msgid.link/20251014100342.978936-3-sshegde@linux.ibm.com
---
 kernel/sched/deadline.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 4d6eaf2..e46df89 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -125,20 +125,11 @@ static inline struct dl_bw *dl_bw_of(int i)
 static inline int dl_bw_cpus(int i)
 {
 	struct root_domain *rd = cpu_rq(i)->rd;
-	int cpus;
 
 	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
 			 "sched RCU must be held");
 
-	if (cpumask_subset(rd->span, cpu_active_mask))
-		return cpumask_weight(rd->span);
-
-	cpus = 0;
-
-	for_each_cpu_and(i, rd->span, cpu_active_mask)
-		cpus++;
-
-	return cpus;
+	return cpumask_weight_and(rd->span, cpu_active_mask);
 }
 
 static inline unsigned long __dl_bw_capacity(const struct cpumask *mask)