[PATCH] mm: fork: fix kernel_stack memcg stats for various stack implementations

[Roman Gushchin]

Depending on CONFIG_VMAP_STACK and the THREAD_SIZE / PAGE_SIZE ratio the
space for task stacks can be allocated using __vmalloc_node_range(),
alloc_pages_node() and kmem_cache_alloc_node().  In the first and the
second cases page->mem_cgroup pointer is set, but in the third it's not:
memcg membership of a slab page should be determined using the
memcg_from_slab_page() function, which looks at
page->slab_cache->memcg_params.memcg .  In this case, using
mod_memcg_page_state() (as in account_kernel_stack()) is incorrect:
page->mem_cgroup pointer is NULL even for pages charged to a non-root
memory cgroup.

It can lead to kernel_stack per-memcg counters permanently showing 0 on
some architectures (depending on the configuration).

In order to fix it, let's introduce a mod_memcg_obj_state() helper, which
takes a pointer to a kernel object as a first argument, uses
mem_cgroup_from_obj() to get a RCU-protected memcg pointer and calls
mod_memcg_state().  It allows to handle all possible configurations
(CONFIG_VMAP_STACK and various THREAD_SIZE/PAGE_SIZE values) without
spilling any memcg/kmem specifics into fork.c .

Note: This is a special version of the patch created for stable
backports. It contains code from the following two patches:
  - mm: memcg/slab: introduce mem_cgroup_from_obj()
  - mm: fork: fix kernel_stack memcg stats for various stack implementations

Fixes: 4d96ba353075 ("mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages")
Signed-off-by: Roman Gushchin <guro@xxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
---
 include/linux/memcontrol.h | 12 ++++++++++++
 kernel/fork.c              |  4 ++--
 mm/memcontrol.c            | 38 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 52 insertions(+), 2 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a7a0a1a5c8d5..e9ba01336d4e 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -695,6 +695,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			int val);
 void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val);
+void mod_memcg_obj_state(void *p, int idx, int val);
 
 static inline void mod_lruvec_state(struct lruvec *lruvec,
 				    enum node_stat_item idx, int val)
@@ -1123,6 +1124,10 @@ static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx,
 	__mod_node_page_state(page_pgdat(page), idx, val);
 }
 
+static inline void mod_memcg_obj_state(void *p, int idx, int val)
+{
+}
+
 static inline
 unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 					    gfp_t gfp_mask,
@@ -1427,6 +1432,8 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
 	return memcg ? memcg->kmemcg_id : -1;
 }
 
+struct mem_cgroup *mem_cgroup_from_obj(void *p);
+
 #else
 
 static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
@@ -1468,6 +1475,11 @@ static inline void memcg_put_cache_ids(void)
 {
 }
 
+static inline struct mem_cgroup *mem_cgroup_from_obj(void *p)
+{
+       return NULL;
+}
+
 #endif /* CONFIG_MEMCG_KMEM */
 
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/kernel/fork.c b/kernel/fork.c
index 080809560072..183a6722dfe2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -397,8 +397,8 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
 		mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
 				    THREAD_SIZE / 1024 * account);
 
-		mod_memcg_page_state(first_page, MEMCG_KERNEL_STACK_KB,
-				     account * (THREAD_SIZE / 1024));
+		mod_memcg_obj_state(stack, MEMCG_KERNEL_STACK_KB,
+				    account * (THREAD_SIZE / 1024));
 	}
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6c83cf4ed970..a0aa1c213231 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -775,6 +775,17 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
 	rcu_read_unlock();
 }
 
+void mod_memcg_obj_state(void *p, int idx, int val)
+{
+	struct mem_cgroup *memcg;
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_obj(p);
+	if (memcg)
+		mod_memcg_state(memcg, idx, val);
+	rcu_read_unlock();
+}
+
 /**
  * __count_memcg_events - account VM events in a cgroup
  * @memcg: the memory cgroup
@@ -2636,6 +2647,33 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 }
 
 #ifdef CONFIG_MEMCG_KMEM
+/*
+ * 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;
+}
+
 static int memcg_alloc_cache_id(void)
 {
 	int id, size;
-- 
2.25.1