The loop starts from the beginning every time we switch to the next
sibling mask. This is the Schlemiel the Painter's style of coding
because we know for sure that nmsk is clear up to the current CPU,
and we can just continue from the next CPU.

Also, we can do it nicer if leverage the dedicated for_each() iterator,
and simplify the logic of clearing a bit in nmsk.

Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 lib/group_cpus.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/lib/group_cpus.c b/lib/group_cpus.c
index ee272c4cefcc..063ed9ae1b8d 100644
--- a/lib/group_cpus.c
+++ b/lib/group_cpus.c
@@ -30,14 +30,14 @@ static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
 
 		/* If the cpu has siblings, use them first */
 		siblmsk = topology_sibling_cpumask(cpu);
-		for (sibl = -1; cpus_per_grp > 0; ) {
-			sibl = cpumask_next(sibl, siblmsk);
-			if (sibl >= nr_cpu_ids)
-				break;
-			if (!cpumask_test_and_clear_cpu(sibl, nmsk))
-				continue;
+		sibl = cpu + 1;
+
+		for_each_cpu_and_from(sibl, siblmsk, nmsk) {
+			if (cpus_per_grp-- == 0)
+				return;
+
+			cpumask_clear_cpu(sibl, nmsk);
 			cpumask_set_cpu(sibl, irqmsk);
-			cpus_per_grp--;
 		}
 	}
 }
-- 
2.40.1

On Thu, Dec 28, 2023 at 12:09:29PM -0800, Yury Norov wrote:
> The loop starts from the beginning every time we switch to the next
> sibling mask. This is the Schlemiel the Painter's style of coding
> because we know for sure that nmsk is clear up to the current CPU,
> and we can just continue from the next CPU.
> 
> Also, we can do it nicer if leverage the dedicated for_each() iterator,
> and simplify the logic of clearing a bit in nmsk.
> 
> Signed-off-by: Yury Norov <yury.norov@gmail.com>
> ---
>  lib/group_cpus.c | 14 +++++++-------
>  1 file changed, 7 insertions(+), 7 deletions(-)
> 
> diff --git a/lib/group_cpus.c b/lib/group_cpus.c
> index ee272c4cefcc..063ed9ae1b8d 100644
> --- a/lib/group_cpus.c
> +++ b/lib/group_cpus.c
> @@ -30,14 +30,14 @@ static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
>  
>  		/* If the cpu has siblings, use them first */
>  		siblmsk = topology_sibling_cpumask(cpu);
> -		for (sibl = -1; cpus_per_grp > 0; ) {
> -			sibl = cpumask_next(sibl, siblmsk);
> -			if (sibl >= nr_cpu_ids)
> -				break;
> -			if (!cpumask_test_and_clear_cpu(sibl, nmsk))
> -				continue;
> +		sibl = cpu + 1;
> +
> +		for_each_cpu_and_from(sibl, siblmsk, nmsk) {
> +			if (cpus_per_grp-- == 0)
> +				return;
> +
> +			cpumask_clear_cpu(sibl, nmsk);
>  			cpumask_set_cpu(sibl, irqmsk);
> -			cpus_per_grp--;

Again, here it is simpler to use for_each_cpu_and() directly, see previous
comment:

https://lore.kernel.org/lkml/ZXgsDcM21H%2F2BTck@fedora/

Meantime patch 1 isn't needed, follows this easier proposal:

diff --git a/lib/group_cpus.c b/lib/group_cpus.c
index ee272c4cefcc..564d8e817f65 100644
--- a/lib/group_cpus.c
+++ b/lib/group_cpus.c
@@ -30,14 +30,11 @@ static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
 
 		/* If the cpu has siblings, use them first */
 		siblmsk = topology_sibling_cpumask(cpu);
-		for (sibl = -1; cpus_per_grp > 0; ) {
-			sibl = cpumask_next(sibl, siblmsk);
-			if (sibl >= nr_cpu_ids)
-				break;
-			if (!cpumask_test_and_clear_cpu(sibl, nmsk))
-				continue;
+		for_each_cpu_and(sibl, siblmsk, nmsk) {
+			cpumask_clear_cpu(sibl, nmsk);
 			cpumask_set_cpu(sibl, irqmsk);
-			cpus_per_grp--;
+			if (--cpus_per_grp == 0)
+				return;
 		}
 	}
 }

Thanks,
Ming