Re: [patch V2 08/10] timer: Implement the hierarchical pull model

[Peter Zijlstra]

On Tue, Apr 18, 2017 at 01:11:10PM +0200, Thomas Gleixner wrote:
> +static struct tmigr_group *tmigr_get_group(unsigned int node, unsigned int lvl)
> +{
> +	struct tmigr_group *group;
> +
> +	/* Try to attach to an exisiting group first */
> +	list_for_each_entry(group, &tmigr_level_list[lvl], list) {
> +		/*
> +		 * If @lvl is below the cross numa node level, check
> +		 * whether this group belongs to the same numa node.
> +		 */
> +		if (lvl < tmigr_crossnode_level && group->numa_node != node)
> +			continue;
> +		/* If the group has capacity, use it */
> +		if (group->num_childs < tmigr_childs_per_group) {
> +			group->num_childs++;
> +			return group;
> +		}

This would result in SMT siblings not sharing groups on regular Intel
systems, right? Since they get enumerated last.

> +	}
> +	/* Allocate and set up a new group */
> +	group = kzalloc_node(sizeof(*group), GFP_KERNEL, node);
> +	if (!group)
> +		return ERR_PTR(-ENOMEM);
> +
> +	if (!zalloc_cpumask_var_node(&group->cpus, GFP_KERNEL, node)) {
> +		kfree(group);
> +		return ERR_PTR(-ENOMEM);
> +	}

So if you place that cpumask last, you can do:

	group = kzalloc_node(sizeof(*group) + cpumask_size(),
	                     GFP_KERNEL, node);

> +	tmigr_init_group(group, lvl, node);
> +	/* Setup successful. Add it to the hierarchy */
> +	list_add(&group->list, &tmigr_level_list[lvl]);
> +	return group;
> +}