We're going to have separate user-configured masks and effective ones.
Eventually configured masks can only be changed by writing cpuset.cpus
and cpuset.mems, and they won't be restricted by parent cpuset. While
effective masks reflect cpu/memory hotplug and hierachical restriction,
and these are the real masks that apply to the tasks in the cpuset.
We calculate effective mask this way:
- top cpuset's effective_mask == online_mask, otherwise
- cpuset's effective_mask == configured_mask & parent effective_mask,
if the result is empty, it inherits parent effective mask.
Those behavior changes are for default hierarchy only. For legacy
hierarchy, effective_mask and configured_mask are the same, so we won't
break old interfaces.
To make cs->effective_{cpus,mems} to be effective masks, we need to
- update the effective masks at hotplug
- update the effective masks at config change
- take on ancestor's mask when the effective mask is empty
The second item is done here. We don't need to treat root_cs specially
in update_cpumasks_hier().
This won't introduce behavior change.
v3:
- add a WARN_ON() to check if effective masks are the same with configured
masks on legacy hierarchy.
- pass trialcs->cpus_allowed to update_cpumasks_hier() and add a comment for
it. Similar change for update_nodemasks_hier(). Suggested by Tejun.
v2:
- revise the comment in update_{cpu,node}masks_hier(), suggested by Tejun.
- fix to use @cp instead of @cs in these two functions.
Signed-off-by: Li Zefan <lizefan@xxxxxxxxxx>
---
kernel/cpuset.c | 88 +++++++++++++++++++++++++++++++++++----------------------
1 file changed, 54 insertions(+), 34 deletions(-)
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 94f651d..da766c3 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -855,36 +855,45 @@ static void update_tasks_cpumask(struct cpuset *cs)
}
/*
- * update_tasks_cpumask_hier - Update the cpumasks of tasks in the hierarchy.
- * @root_cs: the root cpuset of the hierarchy
- * @update_root: update root cpuset or not?
+ * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree
+ * @cs: the cpuset to consider
+ * @new_cpus: temp variable for calculating new effective_cpus
+ *
+ * When congifured cpumask is changed, the effective cpumasks of this cpuset
+ * and all its descendants need to be updated.
*
- * This will update cpumasks of tasks in @root_cs and all other empty cpusets
- * which take on cpumask of @root_cs.
+ * On legacy hierachy, effective_cpus will be the same with cpu_allowed.
*
* Called with cpuset_mutex held
*/
-static void update_tasks_cpumask_hier(struct cpuset *root_cs, bool update_root)
+static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
{
struct cpuset *cp;
struct cgroup_subsys_state *pos_css;
rcu_read_lock();
- cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
- if (cp == root_cs) {
- if (!update_root)
- continue;
- } else {
- /* skip the whole subtree if @cp have some CPU */
- if (!cpumask_empty(cp->cpus_allowed)) {
- pos_css = css_rightmost_descendant(pos_css);
- continue;
- }
+ cpuset_for_each_descendant_pre(cp, pos_css, cs) {
+ struct cpuset *parent = parent_cs(cp);
+
+ cpumask_and(new_cpus, cp->cpus_allowed, parent->effective_cpus);
+
+ /* Skip the whole subtree if the cpumask remains the same. */
+ if (cpumask_equal(new_cpus, cp->effective_cpus)) {
+ pos_css = css_rightmost_descendant(pos_css);
+ continue;
}
+
if (!css_tryget_online(&cp->css))
continue;
rcu_read_unlock();
+ mutex_lock(&callback_mutex);
+ cpumask_copy(cp->effective_cpus, new_cpus);
+ mutex_unlock(&callback_mutex);
+
+ WARN_ON(!cgroup_on_dfl(cp->css.cgroup) &&
+ !cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
+
update_tasks_cpumask(cp);
rcu_read_lock();
@@ -940,7 +949,8 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
mutex_unlock(&callback_mutex);
- update_tasks_cpumask_hier(cs, true);
+ /* use trialcs->cpus_allowed as a temp variable */
+ update_cpumasks_hier(cs, trialcs->cpus_allowed);
if (is_load_balanced)
rebuild_sched_domains_locked();
@@ -1091,36 +1101,45 @@ static void update_tasks_nodemask(struct cpuset *cs)
}
/*
- * update_tasks_nodemask_hier - Update the nodemasks of tasks in the hierarchy.
- * @cs: the root cpuset of the hierarchy
- * @update_root: update the root cpuset or not?
+ * update_nodemasks_hier - Update effective nodemasks and tasks in the subtree
+ * @cs: the cpuset to consider
+ * @new_mems: a temp variable for calculating new effective_mems
+ *
+ * When configured nodemask is changed, the effective nodemasks of this cpuset
+ * and all its descendants need to be updated.
*
- * This will update nodemasks of tasks in @root_cs and all other empty cpusets
- * which take on nodemask of @root_cs.
+ * On legacy hiearchy, effective_mems will be the same with mems_allowed.
*
* Called with cpuset_mutex held
*/
-static void update_tasks_nodemask_hier(struct cpuset *root_cs, bool update_root)
+static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
{
struct cpuset *cp;
struct cgroup_subsys_state *pos_css;
rcu_read_lock();
- cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
- if (cp == root_cs) {
- if (!update_root)
- continue;
- } else {
- /* skip the whole subtree if @cp have some CPU */
- if (!nodes_empty(cp->mems_allowed)) {
- pos_css = css_rightmost_descendant(pos_css);
- continue;
- }
+ cpuset_for_each_descendant_pre(cp, pos_css, cs) {
+ struct cpuset *parent = parent_cs(cp);
+
+ nodes_and(*new_mems, cp->mems_allowed, parent->effective_mems);
+
+ /* Skip the whole subtree if the nodemask remains the same. */
+ if (nodes_equal(*new_mems, cp->effective_mems)) {
+ pos_css = css_rightmost_descendant(pos_css);
+ continue;
}
+
if (!css_tryget_online(&cp->css))
continue;
rcu_read_unlock();
+ mutex_lock(&callback_mutex);
+ cp->effective_mems = *new_mems;
+ mutex_unlock(&callback_mutex);
+
+ WARN_ON(!cgroup_on_dfl(cp->css.cgroup) &&
+ nodes_equal(cp->mems_allowed, cp->effective_mems));
+
update_tasks_nodemask(cp);
rcu_read_lock();
@@ -1188,7 +1207,8 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
cs->mems_allowed = trialcs->mems_allowed;
mutex_unlock(&callback_mutex);
- update_tasks_nodemask_hier(cs, true);
+ /* use trialcs->mems_allowed as a temp variable */
+ update_nodemasks_hier(cs, &cs->mems_allowed);
done:
return retval;
}
--
1.8.0.2
--
To unsubscribe from this list: send the line "unsubscribe cgroups" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
