Re: [PATCH v10 6/9] cpuset: Make generate_sched_domains() recognize isolated_cpus

[Waiman Long <longman@redhat.com>]

On 06/18/2018 12:14 PM, Waiman Long wrote:
> The generate_sched_domains() function and the hotplug code are modified
> to make them use the newly introduced isolated_cpus mask for schedule
> domains generation.
>
> Signed-off-by: Waiman Long <longman@redhat.com>
> ---
>  kernel/cgroup/cpuset.c | 24 ++++++++++++++++++++----
>  1 file changed, 20 insertions(+), 4 deletions(-)
>
> diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
> index cfc9b7b..5ee4239 100644
> --- a/kernel/cgroup/cpuset.c
> +++ b/kernel/cgroup/cpuset.c
> @@ -672,13 +672,14 @@ static int generate_sched_domains(cpumask_var_t **domains,
>  	int ndoms = 0;		/* number of sched domains in result */
>  	int nslot;		/* next empty doms[] struct cpumask slot */
>  	struct cgroup_subsys_state *pos_css;
> +	bool root_load_balance = is_sched_load_balance(&top_cpuset);
>  
>  	doms = NULL;
>  	dattr = NULL;
>  	csa = NULL;
>  
>  	/* Special case for the 99% of systems with one, full, sched domain */
> -	if (is_sched_load_balance(&top_cpuset)) {
> +	if (root_load_balance && !top_cpuset.isolation_count) {
>  		ndoms = 1;
>  		doms = alloc_sched_domains(ndoms);
>  		if (!doms)
> @@ -701,6 +702,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
>  	csn = 0;
>  
>  	rcu_read_lock();
> +	if (root_load_balance)
> +		csa[csn++] = &top_cpuset;
>  	cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) {
>  		if (cp == &top_cpuset)
>  			continue;
> @@ -711,6 +714,9 @@ static int generate_sched_domains(cpumask_var_t **domains,
>  		 * parent's cpus, so just skip them, and then we call
>  		 * update_domain_attr_tree() to calc relax_domain_level of
>  		 * the corresponding sched domain.
> +		 *
> +		 * If root is load-balancing, we can skip @cp if it
> +		 * is a subset of the root's effective_cpus.
>  		 */
>  		if (!cpumask_empty(cp->cpus_allowed) &&
>  		    !(is_sched_load_balance(cp) &&
> @@ -718,11 +724,16 @@ static int generate_sched_domains(cpumask_var_t **domains,
>  					 housekeeping_cpumask(HK_FLAG_DOMAIN))))
>  			continue;
>  
> +		if (root_load_balance &&
> +		    cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus))
> +			continue;
> +
>  		if (is_sched_load_balance(cp))
>  			csa[csn++] = cp;
>  
> -		/* skip @cp's subtree */
> -		pos_css = css_rightmost_descendant(pos_css);
> +		/* skip @cp's subtree if not a scheduling domain root */
> +		if (!is_sched_domain_root(cp))
> +			pos_css = css_rightmost_descendant(pos_css);
>  	}
>  	rcu_read_unlock();
>  
> @@ -849,7 +860,12 @@ static void rebuild_sched_domains_locked(void)
>  	 * passing doms with offlined cpu to partition_sched_domains().
>  	 * Anyways, hotplug work item will rebuild sched domains.
>  	 */
> -	if (!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
> +	if (!top_cpuset.isolation_count &&
> +	    !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
> +		goto out;
> +
> +	if (top_cpuset.isolation_count &&
> +	   !cpumask_subset(top_cpuset.effective_cpus, cpu_active_mask))
>  		goto out;
>  
>  	/* Generate domain masks and attrs */

Sorry, that one is bogus. Please ignore that.

NAK