[PATCH] mm: memcg/slab: introduce mem_cgroup_from_obj()

[Roman Gushchin]

Sometimes we need to get a memcg pointer from a charged kernel object.
The right way to get it depends on whether it's a proper slab object
or it's backed by raw pages (e.g. it's a vmalloc alloction). In the
first case the kmem_cache->memcg_params.memcg indirection should be
used; in other cases it's just page->mem_cgroup.

To simplify this task and hide the implementation details let's
introduce a mem_cgroup_from_obj() helper, which takes a pointer
to any kernel object and returns a valid memcg pointer or NULL.

Passing a kernel address rather than a pointer to a page will allow
to use this helper for per-object (rather than per-page) tracked
objects in the future.

The caller is still responsible to ensure that the returned memcg
isn't going away underneath: take the rcu read lock, cgroup mutex etc;
depending on the context.

mem_cgroup_from_kmem() defined in mm/list_lru.c is now obsolete
and can be removed.

Signed-off-by: Roman Gushchin <guro@xxxxxx>
Acked-by: Yafang Shao <laoar.shao@xxxxxxxxx>
---
 include/linux/memcontrol.h |  7 +++++++
 mm/list_lru.c              | 12 +-----------
 mm/memcontrol.c            | 32 +++++++++++++++++++++++++++++---
 3 files changed, 37 insertions(+), 14 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a7a0a1a5c8d5..292729a1b8c6 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -420,6 +420,8 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
 
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 
+struct mem_cgroup *mem_cgroup_from_obj(void *p);
+
 struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
 
 struct mem_cgroup *get_mem_cgroup_from_page(struct page *page);
@@ -912,6 +914,11 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 	return true;
 }
 
+static inline struct mem_cgroup *mem_cgroup_from_obj(void *p)
+{
+	return NULL;
+}
+
 static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 {
 	return NULL;
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 0f1f6b06b7f3..8de5e3784ee4 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -57,16 +57,6 @@ list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx)
 	return &nlru->lru;
 }
 
-static __always_inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr)
-{
-	struct page *page;
-
-	if (!memcg_kmem_enabled())
-		return NULL;
-	page = virt_to_head_page(ptr);
-	return memcg_from_slab_page(page);
-}
-
 static inline struct list_lru_one *
 list_lru_from_kmem(struct list_lru_node *nlru, void *ptr,
 		   struct mem_cgroup **memcg_ptr)
@@ -77,7 +67,7 @@ list_lru_from_kmem(struct list_lru_node *nlru, void *ptr,
 	if (!nlru->memcg_lrus)
 		goto out;
 
-	memcg = mem_cgroup_from_kmem(ptr);
+	memcg = mem_cgroup_from_obj(ptr);
 	if (!memcg)
 		goto out;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d4394ae4e5be..e768e8d87704 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -757,13 +757,12 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 
 void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
 {
-	struct page *page = virt_to_head_page(p);
-	pg_data_t *pgdat = page_pgdat(page);
+	pg_data_t *pgdat = page_pgdat(virt_to_page(p));
 	struct mem_cgroup *memcg;
 	struct lruvec *lruvec;
 
 	rcu_read_lock();
-	memcg = memcg_from_slab_page(page);
+	memcg = mem_cgroup_from_obj(p);
 
 	/* Untracked pages have no memcg, no lruvec. Update only the node */
 	if (!memcg || memcg == root_mem_cgroup) {
@@ -2635,6 +2634,33 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 		unlock_page_lru(page, isolated);
 }
 
+/*
+ * Returns a pointer to the memory cgroup to which the kernel object is charged.
+ *
+ * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(),
+ * cgroup_mutex, etc.
+ */
+struct mem_cgroup *mem_cgroup_from_obj(void *p)
+{
+	struct page *page;
+
+	if (mem_cgroup_disabled())
+		return NULL;
+
+	page = virt_to_head_page(p);
+
+	/*
+	 * Slab pages don't have page->mem_cgroup set because corresponding
+	 * kmem caches can be reparented during the lifetime. That's why
+	 * memcg_from_slab_page() should be used instead.
+	 */
+	if (PageSlab(page))
+		return memcg_from_slab_page(page);
+
+	/* All other pages use page->mem_cgroup */
+	return page->mem_cgroup;
+}
+
 #ifdef CONFIG_MEMCG_KMEM
 static int memcg_alloc_cache_id(void)
 {
-- 
2.17.1