Re: [PATCH v3 1/2] sched: Create architecture specific sched domain distances

["Chen, Yu C" <yu.c.chen@intel.com>]

On 9/12/2025 2:30 AM, Tim Chen wrote:
> Allow architecture specific sched domain NUMA distances that can be
> modified from NUMA node distances for the purpose of building NUMA
> sched domains.
> 
> The actual NUMA distances are kept separately.  This allows for NUMA
> domain levels modification when building sched domains for specific
> architectures.
> 
> Consolidate the recording of unique NUMA distances in an array to
> sched_record_numa_dist() so the function can be reused to record NUMA
> distances when the NUMA distance metric is changed.
> 
> No functional change if there's no arch specific NUMA distances
> are being defined.
> 

[snip]

> +
> +void sched_init_numa(int offline_node)
> +{
> +	struct sched_domain_topology_level *tl;
> +	int nr_levels, nr_node_levels;
> +	int i, j;
> +	int *distances, *domain_distances;
> +	struct cpumask ***masks;
> +
> +	if (sched_record_numa_dist(offline_node, numa_node_dist, &distances,
> +				   &nr_node_levels))
> +		return;
> +
> +	WRITE_ONCE(sched_avg_remote_numa_distance,
> +		   avg_remote_numa_distance(offline_node));
> +
> +	if (sched_record_numa_dist(offline_node,
> +				   arch_sched_node_distance, &domain_distances,
> +				   &nr_levels)) {
> +		kfree(distances);
> +		return;
> +	}
> +	rcu_assign_pointer(sched_numa_node_distance, distances);
> +	WRITE_ONCE(sched_max_numa_distance, distances[nr_node_levels - 1]);

[snip]

> @@ -2022,7 +2097,6 @@ void sched_init_numa(int offline_node)
>   	sched_domain_topology = tl;
>   
>   	sched_domains_numa_levels = nr_levels;
> -	WRITE_ONCE(sched_max_numa_distance, sched_domains_numa_distance[nr_levels - 1]);
>   

Before this patch, sched_max_numa_distance is assigned a valid
value at the end of sched_init_numa(), after sched_domains_numa_masks
  and sched_domain_topology_level are successfully created or appended
, the kzalloc() call should succeed.

Now we assign sched_max_numa_distance earlier, without considering
the status of NUMA sched domains. I think this is intended, because
  sched domains are only for generic load balancing, while
  sched_max_numa_distance is for NUMA load balancing; in theory, they
use different metrics in their strategies. Thus, this change should
not cause any issues.

 From my understanding,

Reviewed-by: Chen Yu <yu.c.chen@intel.com>

thanks,
Chenyu