memcg: reparent list_lrus and free kmemcg_id on css offline
Now, the only reason to keep kmemcg_id till css free is list_lru, which
uses it to distribute elements between per-memcg lists. However, it can
be easily sorted out - we only need to change kmemcg_id of an offline
cgroup to its parent's id, making further list_lru_add()'s add elements to
the parent's list, and then move all elements from the offline cgroup's
list to the one of its parent. It will work, because a racing
list_lru_del() does not need to know the list it is deleting the element
from. It can decrement the wrong nr_items counter though, but the ongoing
reparenting will fix it. After list_lru reparenting is done we are free
to release kmemcg_id saving a valuable slot in a per-memcg array for new
cgroups.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 8d9d168..909eca2 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -100,7 +100,6 @@
spin_lock(&nlru->lock);
l = list_lru_from_kmem(nlru, item);
- WARN_ON_ONCE(l->nr_items < 0);
if (list_empty(item)) {
list_add_tail(item, &l->list);
l->nr_items++;
@@ -123,7 +122,6 @@
if (!list_empty(item)) {
list_del_init(item);
l->nr_items--;
- WARN_ON_ONCE(l->nr_items < 0);
spin_unlock(&nlru->lock);
return true;
}
@@ -156,7 +154,6 @@
spin_lock(&nlru->lock);
l = list_lru_from_memcg_idx(nlru, memcg_idx);
- WARN_ON_ONCE(l->nr_items < 0);
count = l->nr_items;
spin_unlock(&nlru->lock);
@@ -458,6 +455,49 @@
memcg_cancel_update_list_lru(lru, old_size, new_size);
goto out;
}
+
+static void memcg_drain_list_lru_node(struct list_lru_node *nlru,
+ int src_idx, int dst_idx)
+{
+ struct list_lru_one *src, *dst;
+
+ /*
+ * Since list_lru_{add,del} may be called under an IRQ-safe lock,
+ * we have to use IRQ-safe primitives here to avoid deadlock.
+ */
+ spin_lock_irq(&nlru->lock);
+
+ src = list_lru_from_memcg_idx(nlru, src_idx);
+ dst = list_lru_from_memcg_idx(nlru, dst_idx);
+
+ list_splice_init(&src->list, &dst->list);
+ dst->nr_items += src->nr_items;
+ src->nr_items = 0;
+
+ spin_unlock_irq(&nlru->lock);
+}
+
+static void memcg_drain_list_lru(struct list_lru *lru,
+ int src_idx, int dst_idx)
+{
+ int i;
+
+ if (!list_lru_memcg_aware(lru))
+ return;
+
+ for (i = 0; i < nr_node_ids; i++)
+ memcg_drain_list_lru_node(&lru->node[i], src_idx, dst_idx);
+}
+
+void memcg_drain_all_list_lrus(int src_idx, int dst_idx)
+{
+ struct list_lru *lru;
+
+ mutex_lock(&list_lrus_mutex);
+ list_for_each_entry(lru, &list_lrus, list)
+ memcg_drain_list_lru(lru, src_idx, dst_idx);
+ mutex_unlock(&list_lrus_mutex);
+}
#else
static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
{