cgroup: fix RCU accesses around task->cgroups
There are several places in kernel/cgroup.c where task->cgroups is
accessed and modified without going through proper RCU accessors.
None is broken as they're all lock protected accesses; however, this
still triggers sparse RCU address space warnings.
* Consistently use task_css_set() for task->cgroups dereferencing.
* Use RCU_INIT_POINTER() to clear task->cgroups to &init_css_set on
exit.
* Remove unnecessary rcu_dereference_raw() from cset->subsys[]
dereference in cgroup_exit().
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Acked-by: Li Zefan <lizefan@huawei.com>
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2d3a132..ee9f0c1 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -724,7 +724,7 @@
* task can't change groups, so the only thing that can happen
* is that it exits and its css is set back to init_css_set.
*/
- cset = task->cgroups;
+ cset = task_css_set(task);
if (cset == &init_css_set) {
res = &root->top_cgroup;
} else {
@@ -1971,7 +1971,7 @@
* css_set to init_css_set and dropping the old one.
*/
WARN_ON_ONCE(tsk->flags & PF_EXITING);
- old_cset = tsk->cgroups;
+ old_cset = task_css_set(tsk);
task_lock(tsk);
rcu_assign_pointer(tsk->cgroups, new_cset);
@@ -2094,8 +2094,11 @@
* we use find_css_set, which allocates a new one if necessary.
*/
for (i = 0; i < group_size; i++) {
+ struct css_set *old_cset;
+
tc = flex_array_get(group, i);
- tc->cg = find_css_set(tc->task->cgroups, cgrp);
+ old_cset = task_css_set(tc->task);
+ tc->cg = find_css_set(old_cset, cgrp);
if (!tc->cg) {
retval = -ENOMEM;
goto out_put_css_set_refs;
@@ -3012,7 +3015,7 @@
* entry won't be deleted though the process has exited.
*/
if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
- list_add(&p->cg_list, &p->cgroups->tasks);
+ list_add(&p->cg_list, &task_css_set(p)->tasks);
task_unlock(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
@@ -5061,8 +5064,8 @@
void cgroup_fork(struct task_struct *child)
{
task_lock(current);
+ get_css_set(task_css_set(current));
child->cgroups = current->cgroups;
- get_css_set(child->cgroups);
task_unlock(current);
INIT_LIST_HEAD(&child->cg_list);
}
@@ -5097,7 +5100,7 @@
write_lock(&css_set_lock);
task_lock(child);
if (list_empty(&child->cg_list))
- list_add(&child->cg_list, &child->cgroups->tasks);
+ list_add(&child->cg_list, &task_css_set(child)->tasks);
task_unlock(child);
write_unlock(&css_set_lock);
}
@@ -5177,8 +5180,8 @@
/* Reassign the task to the init_css_set. */
task_lock(tsk);
- cset = tsk->cgroups;
- tsk->cgroups = &init_css_set;
+ cset = task_css_set(tsk);
+ RCU_INIT_POINTER(tsk->cgroups, &init_css_set);
if (run_callbacks && need_forkexit_callback) {
/*
@@ -5187,8 +5190,7 @@
*/
for_each_builtin_subsys(ss, i) {
if (ss->exit) {
- struct cgroup *old_cgrp =
- rcu_dereference_raw(cset->subsys[i])->cgroup;
+ struct cgroup *old_cgrp = cset->subsys[i]->cgroup;
struct cgroup *cgrp = task_cgroup(tsk, i);
ss->exit(cgrp, old_cgrp, tsk);
@@ -5555,7 +5557,7 @@
u64 count;
rcu_read_lock();
- count = atomic_read(¤t->cgroups->refcount);
+ count = atomic_read(&task_css_set(current)->refcount);
rcu_read_unlock();
return count;
}