css_sets are hashed by their subsys[] contents and in cgroup_init()
init_css_set is hashed early, before subsystem inits, when all entries
in its subsys[] are NULL, so that cgroup_dfl_root initialization can
find and link to it. As subsystems are initialized,
init_css_set.subsys[] is filled up but the hashing is never updated
making init_css_set hashed in the wrong place. While incorrect, this
doesn't cause a critical failure as css_set management code would
create an identical css_set dynamically.
Fix it by rehashing init_css_set after subsystems are initialized.
While at it, drop unnecessary @key local variable.
Signed-off-by: Tejun Heo <[email protected]>
---
kernel/cgroup.c | 15 +++++++++++----
1 file changed, 11 insertions(+), 4 deletions(-)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -5263,7 +5263,6 @@ static u16 cgroup_disable_mask __initdat
int __init cgroup_init(void)
{
struct cgroup_subsys *ss;
- unsigned long key;
int ssid;
BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16);
@@ -5273,9 +5272,12 @@ int __init cgroup_init(void)
mutex_lock(&cgroup_mutex);
- /* Add init_css_set to the hash table */
- key = css_set_hash(init_css_set.subsys);
- hash_add(css_set_table, &init_css_set.hlist, key);
+ /*
+ * Add init_css_set to the hash table so that dfl_root can link to
+ * it during init.
+ */
+ hash_add(css_set_table, &init_css_set.hlist,
+ css_set_hash(init_css_set.subsys));
BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
@@ -5328,6 +5330,11 @@ int __init cgroup_init(void)
ss->bind(init_css_set.subsys[ssid]);
}
+ /* init_css_set.subsys[] has been updated, re-hash */
+ hash_del(&init_css_set.hlist);
+ hash_add(css_set_table, &init_css_set.hlist,
+ css_set_hash(init_css_set.subsys));
+
WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup"));
WARN_ON(register_filesystem(&cgroup_fs_type));
WARN_ON(register_filesystem(&cgroup2_fs_type));
During task migration, tasks may transfer between two css_sets which
are associated with the same cgroup. If those tasks are the only
tasks in the cgroup, this currently triggers a spurious de-populated
event on the cgroup.
Fix it by bumping up populated count before bumping it down during
migration to ensure that it doesn't reach zero spuriously.
Signed-off-by: Tejun Heo <[email protected]>
---
kernel/cgroup.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -678,6 +678,9 @@ static void css_set_move_task(struct tas
{
lockdep_assert_held(&css_set_lock);
+ if (to_cset && !css_set_populated(to_cset))
+ css_set_update_populated(to_cset, true);
+
if (from_cset) {
struct css_task_iter *it, *pos;
@@ -711,8 +714,6 @@ static void css_set_move_task(struct tas
*/
WARN_ON_ONCE(task->flags & PF_EXITING);
- if (!css_set_populated(to_cset))
- css_set_update_populated(to_cset, true);
rcu_assign_pointer(task->cgroups, to_cset);
list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks :
&to_cset->tasks);
On 2016/3/3 2:07, Tejun Heo wrote:
> css_sets are hashed by their subsys[] contents and in cgroup_init()
> init_css_set is hashed early, before subsystem inits, when all entries
> in its subsys[] are NULL, so that cgroup_dfl_root initialization can
> find and link to it. As subsystems are initialized,
> init_css_set.subsys[] is filled up but the hashing is never updated
> making init_css_set hashed in the wrong place. While incorrect, this
> doesn't cause a critical failure as css_set management code would
> create an identical css_set dynamically.
>
> Fix it by rehashing init_css_set after subsystems are initialized.
> While at it, drop unnecessary @key local variable.
>
> Signed-off-by: Tejun Heo <[email protected]>
For both patches:
Acked-by: Zefan Li <[email protected]>
Applied to cgroup/for-4.6.
Thanks.
--
tejun