[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <d84092a7-fc3d-4c3c-98b3-341d63a21b18@huaweicloud.com>
Date: Sat, 28 Jun 2025 11:09:39 +0800
From: Chen Ridong <chenridong@...weicloud.com>
To: Muchun Song <songmuchun@...edance.com>, hannes@...xchg.org,
mhocko@...nel.org, roman.gushchin@...ux.dev, shakeel.butt@...ux.dev,
muchun.song@...ux.dev, akpm@...ux-foundation.org, david@...morbit.com,
zhengqi.arch@...edance.com, yosry.ahmed@...ux.dev, nphamcs@...il.com,
chengming.zhou@...ux.dev
Cc: linux-kernel@...r.kernel.org, cgroups@...r.kernel.org,
linux-mm@...ck.org, hamzamahfooz@...ux.microsoft.com,
apais@...ux.microsoft.com
Subject: Re: [PATCH RFC 10/28] mm: memcontrol: return root object cgroup for
root memory cgroup
On 2025/4/15 10:45, Muchun Song wrote:
> Memory cgroup functions such as get_mem_cgroup_from_folio() and
> get_mem_cgroup_from_mm() return a valid memory cgroup pointer,
> even for the root memory cgroup. In contrast, the situation for
> object cgroups has been different.
>
> Previously, the root object cgroup couldn't be returned because
> it didn't exist. Now that a valid root object cgroup exists, for
> the sake of consistency, it's necessary to align the behavior of
> object-cgroup-related operations with that of memory cgroup APIs.
>
> Signed-off-by: Muchun Song <songmuchun@...edance.com>
> ---
> include/linux/memcontrol.h | 29 ++++++++++++++++++-------
> mm/memcontrol.c | 44 ++++++++++++++++++++------------------
> mm/percpu.c | 2 +-
> 3 files changed, 45 insertions(+), 30 deletions(-)
>
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index bb4f203733f3..e74922d5755d 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -319,6 +319,7 @@ struct mem_cgroup {
> #define MEMCG_CHARGE_BATCH 64U
>
> extern struct mem_cgroup *root_mem_cgroup;
> +extern struct obj_cgroup *root_obj_cgroup;
>
> enum page_memcg_data_flags {
> /* page->memcg_data is a pointer to an slabobj_ext vector */
> @@ -528,6 +529,11 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
> return (memcg == root_mem_cgroup);
> }
>
> +static inline bool obj_cgroup_is_root(const struct obj_cgroup *objcg)
> +{
> + return objcg == root_obj_cgroup;
> +}
> +
> static inline bool mem_cgroup_disabled(void)
> {
> return !cgroup_subsys_enabled(memory_cgrp_subsys);
> @@ -752,23 +758,26 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
>
> static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg)
> {
> + if (obj_cgroup_is_root(objcg))
> + return true;
> return percpu_ref_tryget(&objcg->refcnt);
> }
>
> -static inline void obj_cgroup_get(struct obj_cgroup *objcg)
> +static inline void obj_cgroup_get_many(struct obj_cgroup *objcg,
> + unsigned long nr)
> {
> - percpu_ref_get(&objcg->refcnt);
> + if (!obj_cgroup_is_root(objcg))
> + percpu_ref_get_many(&objcg->refcnt, nr);
> }
>
> -static inline void obj_cgroup_get_many(struct obj_cgroup *objcg,
> - unsigned long nr)
> +static inline void obj_cgroup_get(struct obj_cgroup *objcg)
> {
> - percpu_ref_get_many(&objcg->refcnt, nr);
> + obj_cgroup_get_many(objcg, 1);
> }
>
> static inline void obj_cgroup_put(struct obj_cgroup *objcg)
> {
> - if (objcg)
> + if (objcg && !obj_cgroup_is_root(objcg))
> percpu_ref_put(&objcg->refcnt);
> }
>
> @@ -1101,6 +1110,11 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
> return true;
> }
>
> +static inline bool obj_cgroup_is_root(const struct obj_cgroup *objcg)
> +{
> + return true;
> +}
> +
> static inline bool mem_cgroup_disabled(void)
> {
> return true;
> @@ -1684,8 +1698,7 @@ static inline struct obj_cgroup *get_obj_cgroup_from_current(void)
> {
> struct obj_cgroup *objcg = current_obj_cgroup();
>
> - if (objcg)
> - obj_cgroup_get(objcg);
> + obj_cgroup_get(objcg);
>
> return objcg;
> }
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index a6362d11b46c..4aadc1b87db3 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -81,6 +81,7 @@ struct cgroup_subsys memory_cgrp_subsys __read_mostly;
> EXPORT_SYMBOL(memory_cgrp_subsys);
>
> struct mem_cgroup *root_mem_cgroup __read_mostly;
> +struct obj_cgroup *root_obj_cgroup __read_mostly;
>
> /* Active memory cgroup to use from an interrupt context */
> DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg);
> @@ -2525,15 +2526,14 @@ struct mem_cgroup *mem_cgroup_from_slab_obj(void *p)
>
> static struct obj_cgroup *__get_obj_cgroup_from_memcg(struct mem_cgroup *memcg)
> {
> - struct obj_cgroup *objcg = NULL;
> + for (; memcg; memcg = parent_mem_cgroup(memcg)) {
> + struct obj_cgroup *objcg = rcu_dereference(memcg->objcg);
>
> - for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) {
> - objcg = rcu_dereference(memcg->objcg);
> if (likely(objcg && obj_cgroup_tryget(objcg)))
> - break;
> - objcg = NULL;
> + return objcg;
> }
> - return objcg;
> +
> + return NULL;
> }
>
It appears that the return NULL statement might be dead code in this
context. And would it be preferable to use return root_obj_cgroup instead?
Best regards,
Ridong
> static struct obj_cgroup *current_objcg_update(void)
> @@ -2604,18 +2604,17 @@ __always_inline struct obj_cgroup *current_obj_cgroup(void)
> * Objcg reference is kept by the task, so it's safe
> * to use the objcg by the current task.
> */
> - return objcg;
> + return objcg ? : root_obj_cgroup;
> }
>
> memcg = this_cpu_read(int_active_memcg);
> if (unlikely(memcg))
> goto from_memcg;
>
> - return NULL;
> + return root_obj_cgroup;
>
> from_memcg:
> - objcg = NULL;
> - for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) {
> + for (; memcg; memcg = parent_mem_cgroup(memcg)) {
> /*
> * Memcg pointer is protected by scope (see set_active_memcg())
> * and is pinning the corresponding objcg, so objcg can't go
> @@ -2624,10 +2623,10 @@ __always_inline struct obj_cgroup *current_obj_cgroup(void)
> */
> objcg = rcu_dereference_check(memcg->objcg, 1);
> if (likely(objcg))
> - break;
> + return objcg;
> }
>
> - return objcg;
> + return root_obj_cgroup;
> }
>
> struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio)
> @@ -2641,14 +2640,8 @@ struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio)
> objcg = __folio_objcg(folio);
> obj_cgroup_get(objcg);
> } else {
> - struct mem_cgroup *memcg;
> -
> rcu_read_lock();
> - memcg = __folio_memcg(folio);
> - if (memcg)
> - objcg = __get_obj_cgroup_from_memcg(memcg);
> - else
> - objcg = NULL;
> + objcg = __get_obj_cgroup_from_memcg(__folio_memcg(folio));
> rcu_read_unlock();
> }
> return objcg;
> @@ -2733,7 +2726,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
> int ret = 0;
>
> objcg = current_obj_cgroup();
> - if (objcg) {
> + if (!obj_cgroup_is_root(objcg)) {
> ret = obj_cgroup_charge_pages(objcg, gfp, 1 << order);
> if (!ret) {
> obj_cgroup_get(objcg);
> @@ -3036,7 +3029,7 @@ bool __memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru,
> * obj_cgroup_get() is used to get a permanent reference.
> */
> objcg = current_obj_cgroup();
> - if (!objcg)
> + if (obj_cgroup_is_root(objcg))
> return true;
>
> /*
> @@ -3708,6 +3701,9 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
> if (!objcg)
> goto free_shrinker;
>
> + if (unlikely(mem_cgroup_is_root(memcg)))
> + root_obj_cgroup = objcg;
> +
> objcg->memcg = memcg;
> rcu_assign_pointer(memcg->objcg, objcg);
> obj_cgroup_get(objcg);
> @@ -5302,6 +5298,9 @@ void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size)
> if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
> return;
>
> + if (obj_cgroup_is_root(objcg))
> + return;
> +
> VM_WARN_ON_ONCE(!(current->flags & PF_MEMALLOC));
>
> /* PF_MEMALLOC context, charging must succeed */
> @@ -5329,6 +5328,9 @@ void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size)
> if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
> return;
>
> + if (obj_cgroup_is_root(objcg))
> + return;
> +
> obj_cgroup_uncharge(objcg, size);
>
> rcu_read_lock();
> diff --git a/mm/percpu.c b/mm/percpu.c
> index b35494c8ede2..3e54c6fca9bd 100644
> --- a/mm/percpu.c
> +++ b/mm/percpu.c
> @@ -1616,7 +1616,7 @@ static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp,
> return true;
>
> objcg = current_obj_cgroup();
> - if (!objcg)
> + if (obj_cgroup_is_root(objcg))
> return true;
>
> if (obj_cgroup_charge(objcg, gfp, pcpu_obj_full_size(size)))
Powered by blists - more mailing lists