Unverified Commit f0e063d2 authored by openeuler-ci-bot's avatar openeuler-ci-bot Committed by Gitee
Browse files

!11421 Some fixes About cpuset partition 

Merge Pull Request from: @ci-robot 
 
PR sync from: Chen Ridong <chenridong@huawei.com>
https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/K5FP3ZRUQS5CY7CWWLYXOSNUPOOUG2EA/ 
Chen Ridong (1):
  cgroup/cpuset: fix panic caused by partcmd_update

Waiman Long (3):
  cgroup/cpuset: Optimize isolated partition only
    generate_sched_domains() calls
  cgroup/cpuset: Fix remote root partition creation problem
  cgroup/cpuset: Clear effective_xcpus on cpus_allowed clearing only if
    cpus.exclusive not set


-- 
2.34.1
 
https://gitee.com/openeuler/kernel/issues/IAOPW2 
 
Link:https://gitee.com/openeuler/kernel/pulls/11421

 

Reviewed-by: default avatarZhang Peng <zhangpeng362@huawei.com>
Signed-off-by: default avatarZhang Peng <zhangpeng362@huawei.com>
parents 37e8f067 aa72549b

kernel/cgroup/cpuset.c

+54 −14
Original line number Diff line number Diff line
@@ -180,7 +180,7 @@ struct cpuset { 
	/* for custom sched domain */

	int relax_domain_level;



	/* number of valid sub-partitions */

	/* number of valid local child partitions */

	int nr_subparts;



	/* partition root state */
@@ -1114,13 +1114,15 @@ static int generate_sched_domains(cpumask_var_t **domains, 
	int nslot;		/* next empty doms[] struct cpumask slot */

	struct cgroup_subsys_state *pos_css;

	bool root_load_balance = is_sched_load_balance(&top_cpuset);

	bool cgrpv2 = cgroup_subsys_on_dfl(cpuset_cgrp_subsys);



	doms = NULL;

	dattr = NULL;

	csa = NULL;



	/* Special case for the 99% of systems with one, full, sched domain */

	if (root_load_balance && !top_cpuset.nr_subparts) {

	if (root_load_balance && cpumask_empty(subpartitions_cpus)) {

single_root_domain:

		ndoms = 1;

		doms = alloc_sched_domains(ndoms);

		if (!doms)
@@ -1148,16 +1150,18 @@ static int generate_sched_domains(cpumask_var_t **domains, 
	cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) {

		if (cp == &top_cpuset)

			continue;



		if (cgrpv2)

			goto v2;



		/*

		 * v1:

		 * Continue traversing beyond @cp iff @cp has some CPUs and

		 * isn't load balancing.  The former is obvious.  The

		 * latter: All child cpusets contain a subset of the

		 * 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) &&
@@ -1165,20 +1169,39 @@ static int generate_sched_domains(cpumask_var_t **domains, 
					 housekeeping_cpumask(HK_TYPE_DOMAIN))))

			continue;



		if (root_load_balance &&

		    cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus))

		if (is_sched_load_balance(cp) &&

		    !cpumask_empty(cp->effective_cpus))

			csa[csn++] = cp;



		/* skip @cp's subtree */

		pos_css = css_rightmost_descendant(pos_css);

		continue;



		if (is_sched_load_balance(cp) &&

v2:

		/*

		 * Only valid partition roots that are not isolated and with

		 * non-empty effective_cpus will be saved into csn[].

		 */

		if ((cp->partition_root_state == PRS_ROOT) &&

		    !cpumask_empty(cp->effective_cpus))

			csa[csn++] = cp;



		/* skip @cp's subtree if not a partition root */

		if (!is_partition_valid(cp))

		/*

		 * Skip @cp's subtree if not a partition root and has no

		 * exclusive CPUs to be granted to child cpusets.

		 */

		if (!is_partition_valid(cp) && cpumask_empty(cp->exclusive_cpus))

			pos_css = css_rightmost_descendant(pos_css);

	}

	rcu_read_unlock();



	/*

	 * If there are only isolated partitions underneath the cgroup root,

	 * we can optimize out unneeded sched domains scanning.

	 */

	if (root_load_balance && (csn == 1))

		goto single_root_domain;



	for (i = 0; i < csn; i++)

		csa[i]->pn = i;

	ndoms = csn;
@@ -1221,6 +1244,20 @@ static int generate_sched_domains(cpumask_var_t **domains, 
	dattr = kmalloc_array(ndoms, sizeof(struct sched_domain_attr),

			      GFP_KERNEL);



	/*

	 * Cgroup v2 doesn't support domain attributes, just set all of them

	 * to SD_ATTR_INIT. Also non-isolating partition root CPUs are a

	 * subset of HK_TYPE_DOMAIN housekeeping CPUs.

	 */

	if (cgrpv2) {

		for (i = 0; i < ndoms; i++) {

			cpumask_copy(doms[i], csa[i]->effective_cpus);

			if (dattr)

				dattr[i] = SD_ATTR_INIT;

		}

		goto done;

	}



	for (nslot = 0, i = 0; i < csn; i++) {

		struct cpuset *a = csa[i];

		struct cpumask *dp;
@@ -1380,7 +1417,7 @@ static void rebuild_sched_domains_locked(void) 
	 * root should be only a subset of the active CPUs.  Since a CPU in any

	 * partition root could be offlined, all must be checked.

	 */

	if (top_cpuset.nr_subparts) {

	if (!cpumask_empty(subpartitions_cpus)) {

		rcu_read_lock();

		cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {

			if (!is_partition_valid(cs)) {
@@ -1954,6 +1991,8 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, 
			part_error = PERR_CPUSEMPTY;

			goto write_error;

		}

		/* Check newmask again, whether cpus are available for parent/cs */

		nocpu |= tasks_nocpu_error(parent, cs, newmask);



		/*

		 * partcmd_update with newmask:
@@ -2496,6 +2535,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, 
	 */

	if (!*buf) {

		cpumask_clear(trialcs->cpus_allowed);

		if (cpumask_empty(trialcs->exclusive_cpus))

			cpumask_clear(trialcs->effective_xcpus);

	} else {

		retval = cpulist_parse(buf, trialcs->cpus_allowed);
@@ -4671,7 +4711,7 @@ static void cpuset_handle_hotplug(void) 
	 * In the rare case that hotplug removes all the cpus in

	 * subpartitions_cpus, we assumed that cpus are updated.

	 */

	if (!cpus_updated && top_cpuset.nr_subparts)

	if (!cpus_updated && !cpumask_empty(subpartitions_cpus))

		cpus_updated = true;



	/* For v1, synchronize cpus_allowed to cpu_active_mask */