| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20210720141834.10624-8-longman@redhat.com>
Date: Tue, 20 Jul 2021 10:18:32 -0400
From: Waiman Long <longman@...hat.com>
To: Tejun Heo <tj@...nel.org>, Zefan Li <lizefan.x@...edance.com>,
Johannes Weiner <hannes@...xchg.org>,
Jonathan Corbet <corbet@....net>, Shuah Khan <shuah@...nel.org>
Cc: cgroups@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-doc@...r.kernel.org, linux-kselftest@...r.kernel.org,
Andrew Morton <akpm@...ux-foundation.org>,
Roman Gushchin <guro@...com>, Phil Auld <pauld@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Juri Lelli <juri.lelli@...hat.com>,
Frederic Weisbecker <frederic@...nel.org>,
Marcelo Tosatti <mtosatti@...hat.com>,
Michal Koutný <mkoutny@...e.com>,
Waiman Long <longman@...hat.com>
Subject: [PATCH v3 7/9] cgroup/cpuset: Allow non-top parent partition root to distribute out all CPUs
Currently, a parent partition root cannot distribute all its CPUs to
child partition roots with no CPUs left. However in some use cases,
a management application may want to create a parent partition root as
a management unit with no task associated with it and has all its CPUs
distributed to various child partition roots dynamically according to
their needs. Leaving a cpu in the parent partition root in such a case is
now a waste.
To accommodate such use cases, a parent partition root can now have
all its CPUs distributed to its child partition roots as long as:
1) it is not the top cpuset; and
2) there is no task directly associated with the parent.
Once an empty parent partition root is formed, no new task can be moved
into it.
Signed-off-by: Waiman Long <longman@...hat.com>
---
kernel/cgroup/cpuset.c | 90 +++++++++++++++++++++++++++++-------------
1 file changed, 63 insertions(+), 27 deletions(-)
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 60562346ecc1..d4d0c091a0d3 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -284,6 +284,11 @@ static inline void notify_partition_change(struct cpuset *cs,
cgroup_file_notify(&cs->partition_file);
}
+static inline int cpuset_has_tasks(const struct cpuset *cs)
+{
+ return cs->css.cgroup->nr_populated_csets;
+}
+
static struct cpuset top_cpuset = {
.flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) |
(1 << CS_MEM_EXCLUSIVE)),
@@ -1191,22 +1196,32 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
if ((cmd != partcmd_update) && css_has_online_children(&cpuset->css))
return -EBUSY;
- /*
- * Enabling partition root is not allowed if not all the CPUs
- * can be granted from parent's effective_cpus or at least one
- * CPU will be left after that.
- */
- if ((cmd == partcmd_enable) &&
- (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) ||
- cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus)))
- return -EINVAL;
-
/*
* A cpumask update cannot make parent's effective_cpus become empty.
*/
adding = deleting = false;
old_prs = new_prs = cpuset->partition_root_state;
if (cmd == partcmd_enable) {
+ bool parent_is_top_cpuset = !parent_cs(parent);
+ bool no_cpu_in_parent = cpumask_equal(cpuset->cpus_allowed,
+ parent->effective_cpus);
+ /*
+ * Enabling partition root is not allowed if not all the CPUs
+ * can be granted from parent's effective_cpus. If the parent
+ * is the top cpuset, at least one CPU must be left after that.
+ */
+ if (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) ||
+ (parent_is_top_cpuset && no_cpu_in_parent))
+ return -EINVAL;
+
+ /*
+ * A non-top parent can be left with no CPU as long as there
+ * is no task directly associated with the parent. For such
+ * a parent, no new task can be moved into it.
+ */
+ if (no_cpu_in_parent && cpuset_has_tasks(parent))
+ return -EINVAL;
+
cpumask_copy(tmp->addmask, cpuset->cpus_allowed);
adding = true;
} else if (cmd == partcmd_disable) {
@@ -1237,9 +1252,10 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
adding = cpumask_andnot(tmp->addmask, tmp->addmask,
parent->subparts_cpus);
/*
- * Return error if parent's effective_cpus could become empty.
+ * Return error if parent's effective_cpus could become empty
+ * and there are tasks in the parent.
*/
- if (adding &&
+ if (adding && cpuset_has_tasks(parent) &&
cpumask_equal(parent->effective_cpus, tmp->addmask)) {
if (!deleting)
return -EINVAL;
@@ -1255,12 +1271,13 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
}
/*
- * Return error if effective_cpus becomes empty or any CPU
- * distributed to child partitions is deleted.
+ * Return error if effective_cpus becomes empty with tasks
+ * or any CPU distributed to child partitions is deleted.
*/
if (deleting &&
(cpumask_intersects(tmp->delmask, cpuset->subparts_cpus) ||
- cpumask_equal(tmp->delmask, cpuset->effective_cpus)))
+ (cpumask_equal(tmp->delmask, cpuset->effective_cpus) &&
+ cpuset_has_tasks(cpuset))))
return -EBUSY;
} else {
/*
@@ -1281,7 +1298,8 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
parent->effective_cpus);
part_error = (is_partition_root(cpuset) &&
!parent->nr_subparts_cpus) ||
- cpumask_equal(tmp->addmask, parent->effective_cpus);
+ (cpumask_equal(tmp->addmask, parent->effective_cpus) &&
+ cpuset_has_tasks(parent));
}
if (cmd == partcmd_update) {
@@ -1388,9 +1406,15 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
/*
* If it becomes empty, inherit the effective mask of the
- * parent, which is guaranteed to have some CPUs.
+ * parent, which is guaranteed to have some CPUs unless
+ * it is a partition root that has explicitly distributed
+ * out all its CPUs.
*/
if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) {
+ if (is_partition_root(cp) &&
+ cpumask_equal(cp->cpus_allowed, cp->subparts_cpus))
+ goto update_parent_subparts;
+
cpumask_copy(tmp->new_cpus, parent->effective_cpus);
if (!cp->use_parent_ecpus) {
cp->use_parent_ecpus = true;
@@ -1412,6 +1436,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
continue;
}
+update_parent_subparts:
/*
* update_parent_subparts_cpumask() should have been called
* for cs already in update_cpumask(). We should also call
@@ -1482,7 +1507,8 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
*/
cpumask_andnot(cp->effective_cpus, cp->effective_cpus,
cp->subparts_cpus);
- WARN_ON_ONCE(cpumask_empty(cp->effective_cpus));
+ WARN_ON_ONCE(cpumask_empty(cp->effective_cpus) &&
+ cpuset_has_tasks(cp));
}
if (new_prs != old_prs)
@@ -1816,7 +1842,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
cp->effective_mems = *new_mems;
spin_unlock_irq(&callback_lock);
- WARN_ON(!is_in_v2_mode() &&
+ WARN_ON_ONCE(!is_in_v2_mode() &&
!nodes_equal(cp->mems_allowed, cp->effective_mems));
update_tasks_nodemask(cp);
@@ -2231,6 +2257,13 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
(cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
goto out_unlock;
+ /*
+ * On default hierarchy, task cannot be moved to a cpuset with empty
+ * effective cpus.
+ */
+ if (is_in_v2_mode() && cpumask_empty(cs->effective_cpus))
+ goto out_unlock;
+
cgroup_taskset_for_each(task, css, tset) {
ret = task_can_attach(task, cs->cpus_allowed);
if (ret)
@@ -3098,7 +3131,8 @@ hotplug_update_tasks(struct cpuset *cs,
struct cpumask *new_cpus, nodemask_t *new_mems,
bool cpus_updated, bool mems_updated)
{
- if (cpumask_empty(new_cpus))
+ /* A partition root is allowed to have empty effective cpus */
+ if (cpumask_empty(new_cpus) && !is_partition_root(cs))
cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus);
if (nodes_empty(*new_mems))
*new_mems = parent_cs(cs)->effective_mems;
@@ -3167,22 +3201,24 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
/*
* In the unlikely event that a partition root has empty
- * effective_cpus, we will have to force any child partitions,
- * if present, to become invalid by setting nr_subparts_cpus to 0
- * without causing itself to become invalid.
+ * effective_cpus with tasks, we will have to force any child
+ * partitions, if present, to become invalid by setting
+ * nr_subparts_cpus to 0 without causing itself to become invalid.
*/
if (is_partition_root(cs) && cs->nr_subparts_cpus &&
- cpumask_empty(&new_cpus)) {
+ cpumask_empty(&new_cpus) && cpuset_has_tasks(cs)) {
cs->nr_subparts_cpus = 0;
cpumask_clear(cs->subparts_cpus);
compute_effective_cpumask(&new_cpus, cs, parent);
}
/*
- * If empty effective_cpus or zero nr_subparts_cpus or its parent
- * becomes erroneous, we have to transition it to the erroneous state.
+ * If empty effective_cpus with tasks or zero nr_subparts_cpus or
+ * its parent becomes erroneous, we have to transition it to the
+ * erroneous state.
*/
- if (is_partition_root(cs) && (cpumask_empty(&new_cpus) ||
+ if (is_partition_root(cs) &&
+ ((cpumask_empty(&new_cpus) && cpuset_has_tasks(cs)) ||
(parent->partition_root_state == PRS_ERROR) ||
!parent->nr_subparts_cpus)) {
int old_prs;
--
2.18.1
Powered by blists - more mailing lists