[PATCH 0/3] Make memcg location more flexible

[PATCH 0/3] Make memcg location more flexible

[Matthew Wilcox (Oracle)]

Different memdescs should have the flexibility to place their memcg
wherever they need to.  That means that instead of indirecting through
lruvec_stat_mod_folio() and extracting the memcg from the folio,
we need an interface which takes the memcg as a parameter.  It turns
out we already need to do that for slabs, and this memcg_stat_mod()
interface also works for that use case.

Matthew Wilcox (Oracle) (3):
  memcg: Add memcg_stat_mod()
  memcg: Simplify mod_lruvec_kmem_state()
  ptdesc: Account page tables to memcgs again

 include/linux/mm.h       | 15 +++++++++++++--
 include/linux/mm_types.h |  6 +++---
 include/linux/vmstat.h   |  9 ++++++++-
 mm/memcontrol.c          | 40 ++++++++++++++--------------------------
 4 files changed, 38 insertions(+), 32 deletions(-)

-- 
2.47.3

[PATCH 1/3] memcg: Add memcg_stat_mod()

[Matthew Wilcox (Oracle)]

This function lets the caller find the memcg somewhere other than
page->memcg_data.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/vmstat.h |  9 ++++++++-
 mm/memcontrol.c        | 23 +++++++++++++----------
 2 files changed, 21 insertions(+), 11 deletions(-)

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 3c9c266cf782..0da38ea25c97 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -518,7 +518,8 @@ static inline const char *vm_event_name(enum vm_event_item item)
 
 void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			int val);
-
+void memcg_stat_mod(struct mem_cgroup *memcg, pg_data_t *pgdat,
+		enum node_stat_item idx, long val);
 void lruvec_stat_mod_folio(struct folio *folio,
 			     enum node_stat_item idx, int val);
 
@@ -536,6 +537,12 @@ static inline void mod_lruvec_state(struct lruvec *lruvec,
 	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
 }
 
+static inline void memcg_stat_mod(struct mem_cgroup *memcg, pg_data_t *pgdat,
+		enum node_stat_item idx, long val)
+{
+	mod_node_page_state(pgdat, idx, val);
+}
+
 static inline void lruvec_stat_mod_folio(struct folio *folio,
 					 enum node_stat_item idx, int val)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a52da3a5e4fd..b356ef312bc2 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -787,24 +787,27 @@ void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 		mod_memcg_lruvec_state(lruvec, idx, val);
 }
 
+void memcg_stat_mod(struct mem_cgroup *memcg, pg_data_t *pgdat,
+		enum node_stat_item idx, long val)
+{
+	/* Untracked pages have no memcg, no lruvec. Update only the node */
+	if (!memcg) {
+		mod_node_page_state(pgdat, idx, val);
+	} else {
+		struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
+		mod_lruvec_state(lruvec, idx, val);
+	}
+}
+
 void lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx,
 			     int val)
 {
 	struct mem_cgroup *memcg;
 	pg_data_t *pgdat = folio_pgdat(folio);
-	struct lruvec *lruvec;
 
 	rcu_read_lock();
 	memcg = folio_memcg(folio);
-	/* Untracked pages have no memcg, no lruvec. Update only the node */
-	if (!memcg) {
-		rcu_read_unlock();
-		mod_node_page_state(pgdat, idx, val);
-		return;
-	}
-
-	lruvec = mem_cgroup_lruvec(memcg, pgdat);
-	mod_lruvec_state(lruvec, idx, val);
+	memcg_stat_mod(memcg, pgdat, idx, val);
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL(lruvec_stat_mod_folio);
-- 
2.47.3

[PATCH 2/3] memcg: Simplify mod_lruvec_kmem_state()

[Matthew Wilcox (Oracle)]

Use the new memcg_stat_mod() which does exactly what
mod_lruvec_kmem_state() needs.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 mm/memcontrol.c | 17 +----------------
 1 file changed, 1 insertion(+), 16 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b356ef312bc2..8d9e4a42aecf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -815,24 +815,9 @@ EXPORT_SYMBOL(lruvec_stat_mod_folio);
 void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
 {
 	pg_data_t *pgdat = page_pgdat(virt_to_page(p));
-	struct mem_cgroup *memcg;
-	struct lruvec *lruvec;
 
 	rcu_read_lock();
-	memcg = mem_cgroup_from_virt(p);
-
-	/*
-	 * Untracked pages have no memcg, no lruvec. Update only the
-	 * node. If we reparent the slab objects to the root memcg,
-	 * when we free the slab object, we need to update the per-memcg
-	 * vmstats to keep it correct for the root memcg.
-	 */
-	if (!memcg) {
-		mod_node_page_state(pgdat, idx, val);
-	} else {
-		lruvec = mem_cgroup_lruvec(memcg, pgdat);
-		mod_lruvec_state(lruvec, idx, val);
-	}
+	memcg_stat_mod(mem_cgroup_from_virt(p), pgdat, idx, val);
 	rcu_read_unlock();
 }
 
-- 
2.47.3

[PATCH 3/3] ptdesc: Account page tables to memcgs again

[Matthew Wilcox (Oracle)]

Commit f0c92726e89f removed the accounting of page tables to memcgs.
Reintroduce it.

Fixes: f0c92726e89f (ptdesc: remove references to folios from __pagetable_ctor() and pagetable_dtor())
Reported-by: Axel Rasmussen <axelrasmussen@google.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/mm.h       | 15 +++++++++++++--
 include/linux/mm_types.h |  6 +++---
 2 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5be3d8a8f806..34bc6f00ed7b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3519,21 +3519,32 @@ static inline unsigned long ptdesc_nr_pages(const struct ptdesc *ptdesc)
 	return compound_nr(ptdesc_page(ptdesc));
 }
 
+static inline struct mem_cgroup *pagetable_memcg(const struct ptdesc *ptdesc)
+{
+#ifdef CONFIG_MEMCG
+	return ptdesc->pt_memcg;
+#else
+	return NULL;
+#endif
+}
+
 static inline void __pagetable_ctor(struct ptdesc *ptdesc)
 {
 	pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags));
+	struct mem_cgroup *memcg = pagetable_memcg(ptdesc);
 
 	__SetPageTable(ptdesc_page(ptdesc));
-	mod_node_page_state(pgdat, NR_PAGETABLE, ptdesc_nr_pages(ptdesc));
+	memcg_stat_mod(memcg, pgdat, NR_PAGETABLE, ptdesc_nr_pages(ptdesc));
 }
 
 static inline void pagetable_dtor(struct ptdesc *ptdesc)
 {
 	pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags));
+	struct mem_cgroup *memcg = pagetable_memcg(ptdesc);
 
 	ptlock_free(ptdesc);
 	__ClearPageTable(ptdesc_page(ptdesc));
-	mod_node_page_state(pgdat, NR_PAGETABLE, -ptdesc_nr_pages(ptdesc));
+	memcg_stat_mod(memcg, pgdat, NR_PAGETABLE, -ptdesc_nr_pages(ptdesc));
 }
 
 static inline void pagetable_dtor_free(struct ptdesc *ptdesc)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 3cc8ae722886..e9b1da04938a 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -564,7 +564,7 @@ FOLIO_MATCH(compound_head, _head_3);
  * @ptl:              Lock for the page table.
  * @__page_type:      Same as page->page_type. Unused for page tables.
  * @__page_refcount:  Same as page refcount.
- * @pt_memcg_data:    Memcg data. Tracked for page tables here.
+ * @pt_memcg:         Memcg that this page table belongs to.
  *
  * This struct overlays struct page for now. Do not modify without a good
  * understanding of the issues.
@@ -602,7 +602,7 @@ struct ptdesc {
 	unsigned int __page_type;
 	atomic_t __page_refcount;
 #ifdef CONFIG_MEMCG
-	unsigned long pt_memcg_data;
+	struct mem_cgroup *pt_memcg;
 #endif
 };
 
@@ -617,7 +617,7 @@ TABLE_MATCH(rcu_head, pt_rcu_head);
 TABLE_MATCH(page_type, __page_type);
 TABLE_MATCH(_refcount, __page_refcount);
 #ifdef CONFIG_MEMCG
-TABLE_MATCH(memcg_data, pt_memcg_data);
+TABLE_MATCH(memcg_data, pt_memcg);
 #endif
 #undef TABLE_MATCH
 static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
-- 
2.47.3

Re: [PATCH 3/3] ptdesc: Account page tables to memcgs again

[Shakeel Butt]

On Wed, Feb 25, 2026 at 04:22:17PM +0000, Matthew Wilcox (Oracle) wrote:
> Commit f0c92726e89f removed the accounting of page tables to memcgs.
> Reintroduce it.
> 
> Fixes: f0c92726e89f (ptdesc: remove references to folios from __pagetable_ctor() and pagetable_dtor())
> Reported-by: Axel Rasmussen <axelrasmussen@google.com>
> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
> ---
>  include/linux/mm.h       | 15 +++++++++++++--
>  include/linux/mm_types.h |  6 +++---
>  2 files changed, 16 insertions(+), 5 deletions(-)
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 5be3d8a8f806..34bc6f00ed7b 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -3519,21 +3519,32 @@ static inline unsigned long ptdesc_nr_pages(const struct ptdesc *ptdesc)
>  	return compound_nr(ptdesc_page(ptdesc));
>  }
>  
> +static inline struct mem_cgroup *pagetable_memcg(const struct ptdesc *ptdesc)
> +{
> +#ifdef CONFIG_MEMCG
> +	return ptdesc->pt_memcg;
> +#else
> +	return NULL;
> +#endif
> +}
> +
>  static inline void __pagetable_ctor(struct ptdesc *ptdesc)
>  {
>  	pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags));
> +	struct mem_cgroup *memcg = pagetable_memcg(ptdesc);
>  
>  	__SetPageTable(ptdesc_page(ptdesc));
> -	mod_node_page_state(pgdat, NR_PAGETABLE, ptdesc_nr_pages(ptdesc));
> +	memcg_stat_mod(memcg, pgdat, NR_PAGETABLE, ptdesc_nr_pages(ptdesc));
>  }
>  
>  static inline void pagetable_dtor(struct ptdesc *ptdesc)
>  {
>  	pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags));
> +	struct mem_cgroup *memcg = pagetable_memcg(ptdesc);
>  
>  	ptlock_free(ptdesc);
>  	__ClearPageTable(ptdesc_page(ptdesc));
> -	mod_node_page_state(pgdat, NR_PAGETABLE, -ptdesc_nr_pages(ptdesc));
> +	memcg_stat_mod(memcg, pgdat, NR_PAGETABLE, -ptdesc_nr_pages(ptdesc));
>  }
>  
>  static inline void pagetable_dtor_free(struct ptdesc *ptdesc)
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index 3cc8ae722886..e9b1da04938a 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -564,7 +564,7 @@ FOLIO_MATCH(compound_head, _head_3);
>   * @ptl:              Lock for the page table.
>   * @__page_type:      Same as page->page_type. Unused for page tables.
>   * @__page_refcount:  Same as page refcount.
> - * @pt_memcg_data:    Memcg data. Tracked for page tables here.
> + * @pt_memcg:         Memcg that this page table belongs to.
>   *
>   * This struct overlays struct page for now. Do not modify without a good
>   * understanding of the issues.
> @@ -602,7 +602,7 @@ struct ptdesc {
>  	unsigned int __page_type;
>  	atomic_t __page_refcount;
>  #ifdef CONFIG_MEMCG
> -	unsigned long pt_memcg_data;
> +	struct mem_cgroup *pt_memcg;

This is kernel memory, so this would be struct obj_cgroup * instead of struct
mem_cgroup pointer. We will need something similar to __folio_objcg(), maybe
__ptdesc_objcg() and then call obj_cgroup_memcg() on it. Basically how
folio_memcg() handles the kernel memory.