* skipped and we should continue the tree walk.
* last_visited css is safe to use because it is
* protected by css_get and the tree walk is rcu safe.
+ *
+ * We do not take a reference on the root of the tree walk
+ * because we might race with the root removal when it would
+ * be the only node in the iterated hierarchy and mem_cgroup_iter
+ * would end up in an endless loop because it expects that at
+ * least one valid node will be returned. Root cannot disappear
+ * because caller of the iterator should hold it already so
+ * skipping css reference should be safe.
*/
if (next_css) {
- if ((next_css->flags & CSS_ONLINE) && css_tryget(next_css))
+ if ((next_css->flags & CSS_ONLINE) &&
+ (next_css == &root->css || css_tryget(next_css)))
return mem_cgroup_from_css(next_css);
- else {
- prev_css = next_css;
- goto skip_node;
- }
+
+ prev_css = next_css;
+ goto skip_node;
}
return NULL;
if (iter->last_dead_count == *sequence) {
smp_rmb();
position = iter->last_visited;
- if (position && !css_tryget(&position->css))
+
+ /*
+ * We cannot take a reference to root because we might race
+ * with root removal and returning NULL would end up in
+ * an endless loop on the iterator user level when root
+ * would be returned all the time.
+ */
+ if (position && position != root &&
+ !css_tryget(&position->css))
position = NULL;
}
return position;
static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
struct mem_cgroup *last_visited,
struct mem_cgroup *new_position,
+ struct mem_cgroup *root,
int sequence)
{
- if (last_visited)
+ /* root reference counting symmetric to mem_cgroup_iter_load */
+ if (last_visited && last_visited != root)
css_put(&last_visited->css);
/*
* We store the sequence count from the time @last_visited was
memcg = __mem_cgroup_iter_next(root, last_visited);
if (reclaim) {
- mem_cgroup_iter_update(iter, last_visited, memcg, seq);
+ mem_cgroup_iter_update(iter, last_visited, memcg, root,
+ seq);
if (!memcg)
iter->generation++;
break;
};
points = oom_badness(task, memcg, NULL, totalpages);
- if (points > chosen_points) {
- if (chosen)
- put_task_struct(chosen);
- chosen = task;
- chosen_points = points;
- get_task_struct(chosen);
- }
+ if (!points || points < chosen_points)
+ continue;
+ /* Prefer thread group leaders for display purposes */
+ if (points == chosen_points &&
+ thread_group_leader(chosen))
+ continue;
+
+ if (chosen)
+ put_task_struct(chosen);
+ chosen = task;
+ chosen_points = points;
+ get_task_struct(chosen);
}
css_task_iter_end(&it);
}
* So if we aren't down to zero, we'll just schedule a worker and try
* again
*/
- if (atomic_read(&cachep->memcg_params->nr_pages) != 0) {
+ if (atomic_read(&cachep->memcg_params->nr_pages) != 0)
kmem_cache_shrink(cachep);
- if (atomic_read(&cachep->memcg_params->nr_pages) == 0)
- return;
- } else
+ else
kmem_cache_destroy(cachep);
}
static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
struct kmem_cache *s)
{
- struct kmem_cache *new;
+ struct kmem_cache *new = NULL;
static char *tmp_name = NULL;
static DEFINE_MUTEX(mutex); /* protects tmp_name */
if (!tmp_name) {
tmp_name = kmalloc(PATH_MAX, GFP_KERNEL);
if (!tmp_name)
- return NULL;
+ goto out;
}
rcu_read_lock();
new = kmem_cache_create_memcg(memcg, tmp_name, s->object_size, s->align,
(s->flags & ~SLAB_PANIC), s->ctor, s);
-
if (new)
new->allocflags |= __GFP_KMEMCG;
else
new = s;
-
+out:
mutex_unlock(&mutex);
return new;
}