Re: [PATCH 22/33] kthread: Include unbound kthreads in the managed affinity list

[Waiman Long <llong@redhat.com>]

On 10/13/25 4:31 PM, Frederic Weisbecker wrote:
> The managed affinity list currently contains only unbound kthreads that
> have affinity preferences. Unbound kthreads globally affine by default
> are outside of the list because their affinity is automatically managed
> by the scheduler (through the fallback housekeeping mask) and by cpuset.
>
> However in order to preserve the preferred affinity of kthreads, cpuset
> will delegate the isolated partition update propagation to the
> housekeeping and kthread code.
>
> Prepare for that with including all unbound kthreads in the managed
> affinity list.
>
> Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
> ---
>   kernel/kthread.c | 59 ++++++++++++++++++++++++------------------------
>   1 file changed, 30 insertions(+), 29 deletions(-)
>
> diff --git a/kernel/kthread.c b/kernel/kthread.c
> index c4dd967e9e9c..cba3d297f267 100644
> --- a/kernel/kthread.c
> +++ b/kernel/kthread.c
> @@ -365,9 +365,10 @@ static void kthread_fetch_affinity(struct kthread *kthread, struct cpumask *cpum
>   	if (kthread->preferred_affinity) {
>   		pref = kthread->preferred_affinity;
>   	} else {
> -		if (WARN_ON_ONCE(kthread->node == NUMA_NO_NODE))
> -			return;
> -		pref = cpumask_of_node(kthread->node);
> +		if (kthread->node == NUMA_NO_NODE)
> +			pref = housekeeping_cpumask(HK_TYPE_KTHREAD);
> +		else
> +			pref = cpumask_of_node(kthread->node);
>   	}
>   
>   	cpumask_and(cpumask, pref, housekeeping_cpumask(HK_TYPE_KTHREAD));
> @@ -380,32 +381,29 @@ static void kthread_affine_node(void)
>   	struct kthread *kthread = to_kthread(current);
>   	cpumask_var_t affinity;
>   
> -	WARN_ON_ONCE(kthread_is_per_cpu(current));
> +	if (WARN_ON_ONCE(kthread_is_per_cpu(current)))
> +		return;
>   
> -	if (kthread->node == NUMA_NO_NODE) {
> -		housekeeping_affine(current, HK_TYPE_KTHREAD);
> -	} else {
> -		if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) {
> -			WARN_ON_ONCE(1);
> -			return;
> -		}
> -
> -		mutex_lock(&kthread_affinity_lock);
> -		WARN_ON_ONCE(!list_empty(&kthread->affinity_node));
> -		list_add_tail(&kthread->affinity_node, &kthread_affinity_list);
> -		/*
> -		 * The node cpumask is racy when read from kthread() but:
> -		 * - a racing CPU going down will either fail on the subsequent
> -		 *   call to set_cpus_allowed_ptr() or be migrated to housekeepers
> -		 *   afterwards by the scheduler.
> -		 * - a racing CPU going up will be handled by kthreads_online_cpu()
> -		 */
> -		kthread_fetch_affinity(kthread, affinity);
> -		set_cpus_allowed_ptr(current, affinity);
> -		mutex_unlock(&kthread_affinity_lock);
> -
> -		free_cpumask_var(affinity);
> +	if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) {
> +		WARN_ON_ONCE(1);
> +		return;
>   	}
> +
> +	mutex_lock(&kthread_affinity_lock);
> +	WARN_ON_ONCE(!list_empty(&kthread->affinity_node));
> +	list_add_tail(&kthread->affinity_node, &kthread_affinity_list);
> +	/*
> +	 * The node cpumask is racy when read from kthread() but:
> +	 * - a racing CPU going down will either fail on the subsequent
> +	 *   call to set_cpus_allowed_ptr() or be migrated to housekeepers
> +	 *   afterwards by the scheduler.
> +	 * - a racing CPU going up will be handled by kthreads_online_cpu()
> +	 */
> +	kthread_fetch_affinity(kthread, affinity);
> +	set_cpus_allowed_ptr(current, affinity);
> +	mutex_unlock(&kthread_affinity_lock);
> +
> +	free_cpumask_var(affinity);
>   }
>   
>   static int kthread(void *_create)
> @@ -924,8 +922,11 @@ static int kthreads_online_cpu(unsigned int cpu)
>   			ret = -EINVAL;
>   			continue;
>   		}
> -		kthread_fetch_affinity(k, affinity);
> -		set_cpus_allowed_ptr(k->task, affinity);
> +
> +		if (k->preferred_affinity || k->node != NUMA_NO_NODE) {
> +			kthread_fetch_affinity(k, affinity);
> +			set_cpus_allowed_ptr(k->task, affinity);
> +		}
>   	}

My understanding of kthreads_online_cpu() is that hotplug won't affect 
the affinity returned from kthread_fetch_affinity(). However, 
set_cpus_allowed_ptr() will mask out all the offline CPUs. So if the 
given "cpu" to be brought online is in the returned affinity, we should 
call set_cpus_allowed_ptr() to add this cpu into its affinity mask 
though the current code will call it even it is not strictly necessary. 
This change will not do this update to NUMA_NO_NODE kthread with no 
preferred_affinity, is this a problem?

Cheers,
Longman