[PATCH v3 1/5] mm: list_lru: allow external numa node and cgroup tracking
From: Nhat Pham
Date: Tue Oct 17 2023 - 19:22:00 EST
The interface of list_lru is based on the assumption that objects are
allocated on the correct node/memcg, with this change it is introduced the
possibility to explicitly specify numa node and memcgroup when adding and
removing objects. This is so that users of list_lru can track node/memcg
of the items outside of the list_lru, like in zswap, where the allocations
can be made by kswapd for data that's charged to a different cgroup.
Signed-off-by: Nhat Pham <nphamcs@xxxxxxxxx>
---
include/linux/list_lru.h | 38 +++++++++++++++++++++++++++++++++++
mm/list_lru.c | 43 +++++++++++++++++++++++++++++++++++-----
2 files changed, 76 insertions(+), 5 deletions(-)
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index b35968ee9fb5..0f5f39cacbbb 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -89,6 +89,24 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren
*/
bool list_lru_add(struct list_lru *lru, struct list_head *item);
+/**
+ * __list_lru_add: add an element to a specific sublist.
+ * @list_lru: the lru pointer
+ * @item: the item to be added.
+ * @memcg: the cgroup of the sublist to add the item to.
+ * @nid: the node id of the sublist to add the item to.
+ *
+ * This function is similar to list_lru_add(), but it allows the caller to
+ * specify the sublist to which the item should be added. This can be useful
+ * when the list_head node is not necessarily in the same cgroup and NUMA node
+ * as the data it represents, such as zswap, where the list_head node could be
+ * from kswapd and the data from a different cgroup altogether.
+ *
+ * Return value: true if the list was updated, false otherwise
+ */
+bool __list_lru_add(struct list_lru *lru, struct list_head *item, int nid,
+ struct mem_cgroup *memcg);
+
/**
* list_lru_del: delete an element to the lru list
* @list_lru: the lru pointer
@@ -102,6 +120,18 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item);
*/
bool list_lru_del(struct list_lru *lru, struct list_head *item);
+/**
+ * __list_lru_del: delete an element from a specific sublist.
+ * @list_lru: the lru pointer
+ * @item: the item to be deleted.
+ * @memcg: the cgroup of the sublist to delete the item from.
+ * @nid: the node id of the sublist to delete the item from.
+ *
+ * Return value: true if the list was updated, false otherwise.
+ */
+bool __list_lru_del(struct list_lru *lru, struct list_head *item, int nid,
+ struct mem_cgroup *memcg);
+
/**
* list_lru_count_one: return the number of objects currently held by @lru
* @lru: the lru pointer.
@@ -136,6 +166,14 @@ static inline unsigned long list_lru_count(struct list_lru *lru)
void list_lru_isolate(struct list_lru_one *list, struct list_head *item);
void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
struct list_head *head);
+/*
+ * list_lru_putback: undo list_lru_isolate.
+ *
+ * Since we might have dropped the LRU lock in between, recompute list_lru_one
+ * from the node's id and memcg.
+ */
+void list_lru_putback(struct list_lru *lru, struct list_head *item, int nid,
+ struct mem_cgroup *memcg);
typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item,
struct list_lru_one *list, spinlock_t *lock, void *cb_arg);
diff --git a/mm/list_lru.c b/mm/list_lru.c
index a05e5bef3b40..63b75163c6ad 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -119,13 +119,22 @@ list_lru_from_kmem(struct list_lru *lru, int nid, void *ptr,
bool list_lru_add(struct list_lru *lru, struct list_head *item)
{
int nid = page_to_nid(virt_to_page(item));
+ struct mem_cgroup *memcg = list_lru_memcg_aware(lru) ?
+ mem_cgroup_from_slab_obj(item) : NULL;
+
+ return __list_lru_add(lru, item, nid, memcg);
+}
+EXPORT_SYMBOL_GPL(list_lru_add);
+
+bool __list_lru_add(struct list_lru *lru, struct list_head *item, int nid,
+ struct mem_cgroup *memcg)
+{
struct list_lru_node *nlru = &lru->node[nid];
- struct mem_cgroup *memcg;
struct list_lru_one *l;
spin_lock(&nlru->lock);
if (list_empty(item)) {
- l = list_lru_from_kmem(lru, nid, item, &memcg);
+ l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
list_add_tail(item, &l->list);
/* Set shrinker bit if the first element was added */
if (!l->nr_items++)
@@ -138,17 +147,27 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item)
spin_unlock(&nlru->lock);
return false;
}
-EXPORT_SYMBOL_GPL(list_lru_add);
+EXPORT_SYMBOL_GPL(__list_lru_add);
bool list_lru_del(struct list_lru *lru, struct list_head *item)
{
int nid = page_to_nid(virt_to_page(item));
+ struct mem_cgroup *memcg = list_lru_memcg_aware(lru) ?
+ mem_cgroup_from_slab_obj(item) : NULL;
+
+ return __list_lru_del(lru, item, nid, memcg);
+}
+EXPORT_SYMBOL_GPL(list_lru_del);
+
+bool __list_lru_del(struct list_lru *lru, struct list_head *item, int nid,
+ struct mem_cgroup *memcg)
+{
struct list_lru_node *nlru = &lru->node[nid];
struct list_lru_one *l;
spin_lock(&nlru->lock);
if (!list_empty(item)) {
- l = list_lru_from_kmem(lru, nid, item, NULL);
+ l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
list_del_init(item);
l->nr_items--;
nlru->nr_items--;
@@ -158,7 +177,7 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
spin_unlock(&nlru->lock);
return false;
}
-EXPORT_SYMBOL_GPL(list_lru_del);
+EXPORT_SYMBOL_GPL(__list_lru_del);
void list_lru_isolate(struct list_lru_one *list, struct list_head *item)
{
@@ -175,6 +194,20 @@ void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
}
EXPORT_SYMBOL_GPL(list_lru_isolate_move);
+void list_lru_putback(struct list_lru *lru, struct list_head *item, int nid,
+ struct mem_cgroup *memcg)
+{
+ struct list_lru_one *list =
+ list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg));
+
+ if (list_empty(item)) {
+ list_add_tail(item, &list->list);
+ if (!list->nr_items++)
+ set_shrinker_bit(memcg, nid, lru_shrinker_id(lru));
+ }
+}
+EXPORT_SYMBOL_GPL(list_lru_putback);
+
unsigned long list_lru_count_one(struct list_lru *lru,
int nid, struct mem_cgroup *memcg)
{
--
2.34.1