summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLi Zefan <lizefan@huawei.com>2013-06-13 15:11:44 +0800
committerTejun Heo <tj@kernel.org>2013-06-13 10:51:22 -0700
commitf047cecf2cfc9595b1f39c9aab383bb0682f5a53 (patch)
treee3cdfd41e39c1a43ab9cba2721efb0aaf000e858
parent88fa523bff295f1d60244a54833480b02f775152 (diff)
cpuset: fix to migrate mm correctly in a corner case
Before moving tasks out of empty cpusets, update_tasks_nodemask() is called, which calls do_migrate_pages(xx, from, to). Then those tasks are moved to an ancestor, and do_migrate_pages() is called again. The first time: from = node_to_be_offlined, to = empty. The second time: from = empty, to = ancestor's nodemask. so looks like no pages will be migrated. Fix this by: - Don't call update_tasks_nodemask() on empty cpusets. - Pass cs->old_mems_allowed to do_migrate_pages(). v4: added comment in cpuset_hotplug_update_tasks() and rephased comment in cpuset_attach(). Signed-off-by: Li Zefan <lizefan@huawei.com> Signed-off-by: Tejun Heo <tj@kernel.org>
-rw-r--r--kernel/cpuset.c25
1 files changed, 19 insertions, 6 deletions
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 3b3fdfdd4d78..4c17d96bd3a5 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1563,9 +1563,18 @@ static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
struct cpuset *mems_oldcs = effective_nodemask_cpuset(oldcs);
mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
- if (is_memory_migrate(cs))
- cpuset_migrate_mm(mm, &mems_oldcs->mems_allowed,
+
+ /*
+ * old_mems_allowed is the same with mems_allowed here, except
+ * if this task is being moved automatically due to hotplug.
+ * In that case @mems_allowed has been updated and is empty,
+ * so @old_mems_allowed is the right nodesets that we migrate
+ * mm from.
+ */
+ if (is_memory_migrate(cs)) {
+ cpuset_migrate_mm(mm, &mems_oldcs->old_mems_allowed,
&cpuset_attach_nodemask_to);
+ }
mmput(mm);
}
@@ -2152,10 +2161,12 @@ retry:
/*
* If sane_behavior flag is set, we need to update tasks' cpumask
- * for empty cpuset to take on ancestor's cpumask.
+ * for empty cpuset to take on ancestor's cpumask. Otherwise, don't
+ * call update_tasks_cpumask() if the cpuset becomes empty, as
+ * the tasks in it will be migrated to an ancestor.
*/
if ((sane && cpumask_empty(cs->cpus_allowed)) ||
- !cpumask_empty(&off_cpus))
+ (!cpumask_empty(&off_cpus) && !cpumask_empty(cs->cpus_allowed)))
update_tasks_cpumask(cs, NULL);
mutex_lock(&callback_mutex);
@@ -2164,10 +2175,12 @@ retry:
/*
* If sane_behavior flag is set, we need to update tasks' nodemask
- * for empty cpuset to take on ancestor's nodemask.
+ * for empty cpuset to take on ancestor's nodemask. Otherwise, don't
+ * call update_tasks_nodemask() if the cpuset becomes empty, as
+ * the tasks in it will be migratd to an ancestor.
*/
if ((sane && nodes_empty(cs->mems_allowed)) ||
- !nodes_empty(off_mems))
+ (!nodes_empty(off_mems) && !nodes_empty(cs->mems_allowed)))
update_tasks_nodemask(cs, NULL);
is_empty = cpumask_empty(cs->cpus_allowed) ||