[PATCH v1 7/8] sched/topology: Avoid redundant percpu allocations and bitmap walks in build_sched_domains()

[Tim Chen]

On Thu, 2026-10-15 at 11:33 -0400, Pasha Tatashin wrote:
> During CPU hotplug, build_sched_domains() is invoked on every CPU
> activation and deactivation. Profiling build_sched_domains() on a
> 480-CPU Intel Xeon 6985P-C and a 512-CPU AMD EPYC 9B45 shows several
> sources of avoidable O(N^2) and O(N) work per step:
> 
> 1. build_sched_groups() and build_overlap_sched_groups() iterate over
>    every bit of sched_domain_span(sd) via for_each_cpu_wrap(i, span, cpu)
>    and check cpumask_test_cpu(i, covered) one CPU at a time, even after
>    entire child groups (e.g., 120-CPU NUMA nodes) have been added to
>    covered. Instead, track the remaining uncovered CPUs
>    (cpumask_copy(uncovered, span)), clear each built group's span with
>    cpumask_andnot(), and advance directly to the next uncovered CPU.
> 
> 2. __visit_domain_allocation_hell() and __free_domain_allocs() allocate
>    and free 3 * nr_levels + 2 temporary per-CPU pointer arrays via
>    alloc_percpu() / free_percpu() on every domain rebuild. Reuse the
>    per-CPU pointer arrays across domain rebuilds under
>    sched_domains_mutex, clearing entries in __free_domain_allocs() and
>    only freeing the topology-level arrays when sched_domain_topology is
>    replaced in sched_init_numa() / sched_reset_numa().

sched_domains_mutex does not protect the free:

[snip]

>  #ifdef CONFIG_NUMA
> +static void __sdt_free_percpu(void)
> +{
> +	struct sched_domain_topology_level *tl;
> +
> +	for_each_sd_topology(tl) {
> +		struct sd_data *sdd = &tl->data;
> +

sched_init_numa() and sched_reset_numa() are called from
sched_update_numa(), which runs from sched_cpu_activate() and
sched_cpu_deactivate() without sched_domains_mutex. The free is safe
because every domain builder holds at least cpus_read_lock(), and
sched_update_numa() runs under the hotplug write lock. 

Please fix the changelog and add lockdep_assert_cpus_held()
in __sdt_free_percpu(), so a future caller cannot break this without a warning.



> +		free_percpu(sdd->sd);
> +		sdd->sd = NULL;
> +		free_percpu(sdd->sg);
> +		sdd->sg = NULL;
> +		free_percpu(sdd->sgc);
> +		sdd->sgc = NULL;
> +	}
> +}
> +
>  static int cpu_numa_flags(void)
>  {
>  	return SD_NUMA;
> @@ -2449,6 +2483,7 @@ void sched_init_numa(int offline_node)
>  	/*
>  	 * Copy the default topology bits..
>  	 */
> +	__sdt_free_percpu();
>  	for (i = 0; sched_domain_topology[i].mask; i++)
>  		tl[i] = sched_domain_topology[i];
>  
> @@ -2507,6 +2542,7 @@ static void sched_reset_numa(void)
>  		kfree(masks);
>  	}
>  	if (sched_domain_topology_saved) {
> +		__sdt_free_percpu();
>  		kfree(sched_domain_topology);
>  		sched_domain_topology = sched_domain_topology_saved;
>  		sched_domain_topology_saved = NULL;
> @@ -2708,17 +2744,23 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
>  	for_each_sd_topology(tl) {
>  		struct sd_data *sdd = &tl->data;
>  
> -		sdd->sd = alloc_percpu(struct sched_domain *);
> -		if (!sdd->sd)
> -			return -ENOMEM;
> +		if (!sdd->sd) {
> +			sdd->sd = alloc_percpu(struct sched_domain *);
> +			if (!sdd->sd)
> +				return -ENOMEM;
> +		}
>  
> -		sdd->sg = alloc_percpu(struct sched_group *);
> -		if (!sdd->sg)
> -			return -ENOMEM;
> +		if (!sdd->sg) {
> +			sdd->sg = alloc_percpu(struct sched_group *);
> +			if (!sdd->sg)
> +				return -ENOMEM;
> +		}
>  
> -		sdd->sgc = alloc_percpu(struct sched_group_capacity *);
> -		if (!sdd->sgc)
> -			return -ENOMEM;
> +		if (!sdd->sgc) {
> +			sdd->sgc = alloc_percpu(struct sched_group_capacity *);
> +			if (!sdd->sgc)
> +				return -ENOMEM;
> +		}
>  

Keeping the arrays also means every slot must be NULL when a build 
starts. Patch 5 depends on that: get_group(), 
init_overlap_sched_group() and init_sched_domain_shared() treat a NULL 
slot as "not allocated yet", and the overlap fast path treats 
"sgc->ref > 0" as "set up in this build". An old pointer would pass
these checks and be used without a warning.

The rule holds today, but nothing says so. It also depends on builds
never filling a slot outside cpu_map, because the clearing loops only
visit cpu_map. Please write this down and check it, for example in
__sdt_alloc():


>  		for_each_cpu(j, cpu_map) {
>  			struct sched_domain *sd;

Maybe add

        /*
         * The slot arrays are kept between builds. Every slot for a CPU
         * in cpu_map must be NULL here; lazy allocation treats NULL as
         * "not allocated in this build". claim_allocations() and
         * __sdt_free()/__sds_free() clear the slots, but only for
         * cpu_map, so a build must not fill slots outside cpu_map.
         */
                for_each_cpu(j, cpu_map) {
                        struct sched_domain *sd;

                        WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, j) ||
                                     *per_cpu_ptr(sdd->sg, j) ||
                                     *per_cpu_ptr(sdd->sgc, j));



> @@ -2748,30 +2790,36 @@ static void __sdt_free(const struct cpumask *cpu_map)
>  
>  			if (sdd->sd) {
>  				sd = *per_cpu_ptr(sdd->sd, j);
> -				if (sd && (sd->flags & SD_NUMA))
> -					free_sched_groups(sd->groups, 0);
> -				kfree(*per_cpu_ptr(sdd->sd, j));
> +				if (sd) {
> +					if (sd->flags & SD_NUMA)
> +						free_sched_groups(sd->groups, 0);
> +					kfree(sd);
> +					*per_cpu_ptr(sdd->sd, j) = NULL;
> +				}
>  			}
>  
> -			if (sdd->sg)
> +			if (sdd->sg) {
>  				kfree(*per_cpu_ptr(sdd->sg, j));
> -			if (sdd->sgc)
> +				*per_cpu_ptr(sdd->sg, j) = NULL;
> +			}
> +			if (sdd->sgc) {
>  				kfree(*per_cpu_ptr(sdd->sgc, j));
> +				*per_cpu_ptr(sdd->sgc, j) = NULL;
> +			}
>  		}
> -		free_percpu(sdd->sd);
> -		sdd->sd = NULL;
> -		free_percpu(sdd->sg);
> -		sdd->sg = NULL;
> -		free_percpu(sdd->sgc);
> -		sdd->sgc = NULL;
>  	}
>  }
>  
> +static struct sched_domain_shared * __percpu *sched_domains_sds;
> +
>  static int __sds_alloc(struct s_data *d, const struct cpumask *cpu_map)
>  {

and maybe similar check 

        for_each_cpu(j, cpu_map)
                WARN_ON_ONCE(*per_cpu_ptr(d->sds, j));

> -	d->sds = alloc_percpu(struct sched_domain_shared *);
> -	if (!d->sds)
> -		return -ENOMEM;
> +	if (!sched_domains_sds) {
> +		sched_domains_sds = alloc_percpu(struct sched_domain_shared *);
> +		if (!sched_domains_sds)
> +			return -ENOMEM;
> +	}
> +	d->sds = sched_domains_sds;
>  
>  	return 0;
>  }


Thanks.

Tim