Commit 7d709f49babc ("vmscan,cgroup: apply mems_effective to reclaim")
introduces the cpuset.mems_effective check and applies it to
can_demote(). However, it checks only the nodes in the immediate next
demotion hierarchy and does not check all allowed demotion targets.
This can cause pages to never be demoted if the nodes in the next
demotion hierarchy are not set in mems_effective.

To address the bug, use mem_cgroup_filter_mems_allowed() to filter
out allowed targets obtained from node_get_allowed_targets(). Also
remove some unused functions.

Fixes: 7d709f49babc ("vmscan,cgroup: apply mems_effective to reclaim")
Signed-off-by: Bing Jiao <bingjiao@google.com>
---
 include/linux/cpuset.h     |  6 ------
 include/linux/memcontrol.h |  7 -------
 kernel/cgroup/cpuset.c     | 28 ++++------------------------
 mm/memcontrol.c            |  5 -----
 mm/vmscan.c                | 14 ++++++++------
 5 files changed, 12 insertions(+), 48 deletions(-)

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 0e94548e2d24..ed7c27276e71 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -174,7 +174,6 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 	task_unlock(current);
 }
 
-extern bool cpuset_node_allowed(struct cgroup *cgroup, int nid);
 extern void cpuset_node_filter_allowed(struct cgroup *cgroup, nodemask_t *mask);
 #else /* !CONFIG_CPUSETS */
 
@@ -302,11 +301,6 @@ static inline bool read_mems_allowed_retry(unsigned int seq)
 	return false;
 }
 
-static inline bool cpuset_node_allowed(struct cgroup *cgroup, int nid)
-{
-	return true;
-}
-
 static inline void cpuset_node_filter_allowed(struct cgroup *cgroup,
 					      nodemask_t *mask)
 {
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 7cfd71c57caa..41aab33499b5 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1740,8 +1740,6 @@ static inline void count_objcg_events(struct obj_cgroup *objcg,
 	rcu_read_unlock();
 }
 
-bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid);
-
 void mem_cgroup_filter_mems_allowed(struct mem_cgroup *memcg, nodemask_t *mask);
 
 void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg);
@@ -1813,11 +1811,6 @@ static inline ino_t page_cgroup_ino(struct page *page)
 	return 0;
 }
 
-static inline bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid)
-{
-	return true;
-}
-
 static inline bool mem_cgroup_filter_mems_allowed(struct mem_cgroup *memcg,
 						  nodemask_t *mask)
 {
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 2925bd6bca91..339779571508 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -4416,11 +4416,10 @@ bool cpuset_current_node_allowed(int node, gfp_t gfp_mask)
 	return allowed;
 }
 
-bool cpuset_node_allowed(struct cgroup *cgroup, int nid)
+void cpuset_node_filter_allowed(struct cgroup *cgroup, nodemask_t *mask)
 {
 	struct cgroup_subsys_state *css;
 	struct cpuset *cs;
-	bool allowed;
 
 	/*
 	 * In v1, mem_cgroup and cpuset are unlikely in the same hierarchy
@@ -4428,15 +4427,15 @@ bool cpuset_node_allowed(struct cgroup *cgroup, int nid)
 	 * so return true to avoid taking a global lock on the empty check.
 	 */
 	if (!cpuset_v2())
-		return true;
+		return;
 
 	css = cgroup_get_e_css(cgroup, &cpuset_cgrp_subsys);
 	if (!css)
-		return true;
+		return;
 
 	/*
 	 * Normally, accessing effective_mems would require the cpuset_mutex
-	 * or callback_lock - but node_isset is atomic and the reference
+	 * or callback_lock - but it is acceptable and the reference
 	 * taken via cgroup_get_e_css is sufficient to protect css.
 	 *
 	 * Since this interface is intended for use by migration paths, we
@@ -4447,25 +4446,6 @@ bool cpuset_node_allowed(struct cgroup *cgroup, int nid)
 	 * cannot make strong isolation guarantees, so this is acceptable.
 	 */
 	cs = container_of(css, struct cpuset, css);
-	allowed = node_isset(nid, cs->effective_mems);
-	css_put(css);
-	return allowed;
-}
-
-void cpuset_node_filter_allowed(struct cgroup *cgroup, nodemask_t *mask)
-{
-	struct cgroup_subsys_state *css;
-	struct cpuset *cs;
-
-	if (!cpuset_v2())
-		return;
-
-	css = cgroup_get_e_css(cgroup, &cpuset_cgrp_subsys);
-	if (!css)
-		return;
-
-	/* Follows the same assumption in cpuset_node_allowed() */
-	cs = container_of(css, struct cpuset, css);
 	nodes_and(*mask, *mask, cs->effective_mems);
 	css_put(css);
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f414653867de..ebf5df3c8ca1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5597,11 +5597,6 @@ subsys_initcall(mem_cgroup_swap_init);
 
 #endif /* CONFIG_SWAP */
 
-bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid)
-{
-	return memcg ? cpuset_node_allowed(memcg->css.cgroup, nid) : true;
-}
-
 void mem_cgroup_filter_mems_allowed(struct mem_cgroup *memcg, nodemask_t *mask)
 {
 	if (memcg)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4d23c491e914..fa4d51af7f44 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -344,19 +344,21 @@ static void flush_reclaim_state(struct scan_control *sc)
 static bool can_demote(int nid, struct scan_control *sc,
 		       struct mem_cgroup *memcg)
 {
-	int demotion_nid;
+	struct pglist_data *pgdat = NODE_DATA(nid);
+	nodemask_t allowed_mask;
 
-	if (!numa_demotion_enabled)
+	if (!pgdat || !numa_demotion_enabled)
 		return false;
 	if (sc && sc->no_demotion)
 		return false;
 
-	demotion_nid = next_demotion_node(nid);
-	if (demotion_nid == NUMA_NO_NODE)
+	node_get_allowed_targets(pgdat, &allowed_mask);
+	if (nodes_empty(allowed_mask))
 		return false;
 
-	/* If demotion node isn't in the cgroup's mems_allowed, fall back */
-	return mem_cgroup_node_allowed(memcg, demotion_nid);
+	/* Filter the given nmask based on cpuset.mems.allowed */
+	mem_cgroup_filter_mems_allowed(memcg, &allowed_mask);
+	return !nodes_empty(allowed_mask);
 }
 
 static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
-- 
2.52.0.351.gbe84eed79e-goog

On 2025/12/22 7:36, Bing Jiao wrote:
> Commit 7d709f49babc ("vmscan,cgroup: apply mems_effective to reclaim")
> introduces the cpuset.mems_effective check and applies it to
> can_demote(). However, it checks only the nodes in the immediate next
> demotion hierarchy and does not check all allowed demotion targets.
> This can cause pages to never be demoted if the nodes in the next
> demotion hierarchy are not set in mems_effective.
> 
> To address the bug, use mem_cgroup_filter_mems_allowed() to filter
> out allowed targets obtained from node_get_allowed_targets(). Also
> remove some unused functions.
> 
> Fixes: 7d709f49babc ("vmscan,cgroup: apply mems_effective to reclaim")
> Signed-off-by: Bing Jiao <bingjiao@google.com>
> ---
>  include/linux/cpuset.h     |  6 ------
>  include/linux/memcontrol.h |  7 -------
>  kernel/cgroup/cpuset.c     | 28 ++++------------------------
>  mm/memcontrol.c            |  5 -----
>  mm/vmscan.c                | 14 ++++++++------
>  5 files changed, 12 insertions(+), 48 deletions(-)
> 
> diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
> index 0e94548e2d24..ed7c27276e71 100644
> --- a/include/linux/cpuset.h
> +++ b/include/linux/cpuset.h
> @@ -174,7 +174,6 @@ static inline void set_mems_allowed(nodemask_t nodemask)
>  	task_unlock(current);
>  }
>  
> -extern bool cpuset_node_allowed(struct cgroup *cgroup, int nid);
>  extern void cpuset_node_filter_allowed(struct cgroup *cgroup, nodemask_t *mask);
>  #else /* !CONFIG_CPUSETS */
>  
> @@ -302,11 +301,6 @@ static inline bool read_mems_allowed_retry(unsigned int seq)
>  	return false;
>  }
>  
> -static inline bool cpuset_node_allowed(struct cgroup *cgroup, int nid)
> -{
> -	return true;
> -}
> -
>  static inline void cpuset_node_filter_allowed(struct cgroup *cgroup,
>  					      nodemask_t *mask)
>  {
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 7cfd71c57caa..41aab33499b5 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -1740,8 +1740,6 @@ static inline void count_objcg_events(struct obj_cgroup *objcg,
>  	rcu_read_unlock();
>  }
>  
> -bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid);
> -
>  void mem_cgroup_filter_mems_allowed(struct mem_cgroup *memcg, nodemask_t *mask);
>  
>  void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg);
> @@ -1813,11 +1811,6 @@ static inline ino_t page_cgroup_ino(struct page *page)
>  	return 0;
>  }
>  
> -static inline bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid)
> -{
> -	return true;
> -}
> -
>  static inline bool mem_cgroup_filter_mems_allowed(struct mem_cgroup *memcg,
>  						  nodemask_t *mask)
>  {
> diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
> index 2925bd6bca91..339779571508 100644
> --- a/kernel/cgroup/cpuset.c
> +++ b/kernel/cgroup/cpuset.c
> @@ -4416,11 +4416,10 @@ bool cpuset_current_node_allowed(int node, gfp_t gfp_mask)
>  	return allowed;
>  }
>  
> -bool cpuset_node_allowed(struct cgroup *cgroup, int nid)
> +void cpuset_node_filter_allowed(struct cgroup *cgroup, nodemask_t *mask)
>  {
>  	struct cgroup_subsys_state *css;
>  	struct cpuset *cs;
> -	bool allowed;
>  
>  	/*
>  	 * In v1, mem_cgroup and cpuset are unlikely in the same hierarchy
> @@ -4428,15 +4427,15 @@ bool cpuset_node_allowed(struct cgroup *cgroup, int nid)
>  	 * so return true to avoid taking a global lock on the empty check.
>  	 */
>  	if (!cpuset_v2())
> -		return true;
> +		return;
>  
>  	css = cgroup_get_e_css(cgroup, &cpuset_cgrp_subsys);
>  	if (!css)
> -		return true;
> +		return;
>  
>  	/*
>  	 * Normally, accessing effective_mems would require the cpuset_mutex
> -	 * or callback_lock - but node_isset is atomic and the reference
> +	 * or callback_lock - but it is acceptable and the reference
>  	 * taken via cgroup_get_e_css is sufficient to protect css.
>  	 *
>  	 * Since this interface is intended for use by migration paths, we
> @@ -4447,25 +4446,6 @@ bool cpuset_node_allowed(struct cgroup *cgroup, int nid)
>  	 * cannot make strong isolation guarantees, so this is acceptable.
>  	 */
>  	cs = container_of(css, struct cpuset, css);
> -	allowed = node_isset(nid, cs->effective_mems);
> -	css_put(css);
> -	return allowed;
> -}
> -
> -void cpuset_node_filter_allowed(struct cgroup *cgroup, nodemask_t *mask)
> -{
> -	struct cgroup_subsys_state *css;
> -	struct cpuset *cs;
> -
> -	if (!cpuset_v2())
> -		return;
> -
> -	css = cgroup_get_e_css(cgroup, &cpuset_cgrp_subsys);
> -	if (!css)
> -		return;
> -
> -	/* Follows the same assumption in cpuset_node_allowed() */
> -	cs = container_of(css, struct cpuset, css);
>  	nodes_and(*mask, *mask, cs->effective_mems);
>  	css_put(css);
>  }

Oh, I see you merged these two functions here.

However, I think cpuset_get_mem_allowed would be more versatile in general use.

You can then check whether the returned nodemask intersects with your target mask. In the future,
there may be scenarios where users simply want to retrieve the effective masks directly.

> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index f414653867de..ebf5df3c8ca1 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -5597,11 +5597,6 @@ subsys_initcall(mem_cgroup_swap_init);
>  
>  #endif /* CONFIG_SWAP */
>  
> -bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid)
> -{
> -	return memcg ? cpuset_node_allowed(memcg->css.cgroup, nid) : true;
> -}
> -
>  void mem_cgroup_filter_mems_allowed(struct mem_cgroup *memcg, nodemask_t *mask)
>  {
>  	if (memcg)
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 4d23c491e914..fa4d51af7f44 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -344,19 +344,21 @@ static void flush_reclaim_state(struct scan_control *sc)
>  static bool can_demote(int nid, struct scan_control *sc,
>  		       struct mem_cgroup *memcg)
>  {
> -	int demotion_nid;
> +	struct pglist_data *pgdat = NODE_DATA(nid);
> +	nodemask_t allowed_mask;
>  
> -	if (!numa_demotion_enabled)
> +	if (!pgdat || !numa_demotion_enabled)
>  		return false;
>  	if (sc && sc->no_demotion)
>  		return false;
>  
> -	demotion_nid = next_demotion_node(nid);
> -	if (demotion_nid == NUMA_NO_NODE)
> +	node_get_allowed_targets(pgdat, &allowed_mask);
> +	if (nodes_empty(allowed_mask))
>  		return false;
>  
> -	/* If demotion node isn't in the cgroup's mems_allowed, fall back */
> -	return mem_cgroup_node_allowed(memcg, demotion_nid);
> +	/* Filter the given nmask based on cpuset.mems.allowed */
> +	mem_cgroup_filter_mems_allowed(memcg, &allowed_mask);
> +	return !nodes_empty(allowed_mask);
>  }
>  
>  static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,

-- 
Best regards,
Ridong

On Mon, Dec 22, 2025 at 10:51:49AM +0800, Chen Ridong wrote:
>
>
> On 2025/12/22 7:36, Bing Jiao wrote:
> > -void cpuset_node_filter_allowed(struct cgroup *cgroup, nodemask_t *mask)
> > -{
> > -	struct cgroup_subsys_state *css;
> > -	struct cpuset *cs;
> > -
> > -	if (!cpuset_v2())
> > -		return;
> > -
> > -	css = cgroup_get_e_css(cgroup, &cpuset_cgrp_subsys);
> > -	if (!css)
> > -		return;
> > -
> > -	/* Follows the same assumption in cpuset_node_allowed() */
> > -	cs = container_of(css, struct cpuset, css);
> >  	nodes_and(*mask, *mask, cs->effective_mems);
> >  	css_put(css);
> >  }
>
> Oh, I see you merged these two functions here.
>
> However, I think cpuset_get_mem_allowed would be more versatile in general use.
>
> You can then check whether the returned nodemask intersects with your target mask. In the future,
> there may be scenarios where users simply want to retrieve the effective masks directly.
>

Hi Ridong, thank you for the suggestions.

I agree that returning a nodemask would provide greater versatility.

I think cpuset_get_mem_allowed_relax() would be a better name,
since we do not need the locking and online mem guarantees
compared to an similar function cpuset_mems_allowed().

Best,
Bing

On 2025/12/22 14:09, Bing Jiao wrote:
> On Mon, Dec 22, 2025 at 10:51:49AM +0800, Chen Ridong wrote:
>>
>>
>> On 2025/12/22 7:36, Bing Jiao wrote:
>>> -void cpuset_node_filter_allowed(struct cgroup *cgroup, nodemask_t *mask)
>>> -{
>>> -	struct cgroup_subsys_state *css;
>>> -	struct cpuset *cs;
>>> -
>>> -	if (!cpuset_v2())
>>> -		return;
>>> -
>>> -	css = cgroup_get_e_css(cgroup, &cpuset_cgrp_subsys);
>>> -	if (!css)
>>> -		return;
>>> -
>>> -	/* Follows the same assumption in cpuset_node_allowed() */
>>> -	cs = container_of(css, struct cpuset, css);
>>>  	nodes_and(*mask, *mask, cs->effective_mems);
>>>  	css_put(css);
>>>  }
>>
>> Oh, I see you merged these two functions here.
>>
>> However, I think cpuset_get_mem_allowed would be more versatile in general use.
>>
>> You can then check whether the returned nodemask intersects with your target mask. In the future,
>> there may be scenarios where users simply want to retrieve the effective masks directly.
>>
> 
> Hi Ridong, thank you for the suggestions.
> 
> I agree that returning a nodemask would provide greater versatility.
> 
> I think cpuset_get_mem_allowed_relax() would be a better name,
> since we do not need the locking and online mem guarantees
> compared to an similar function cpuset_mems_allowed().
> 

I think the key difference between cpuset_mems_allowed and the helper you intend to implement lies
not in locking or online memory guarantees, but in the input parameter: you want to retrieve
cpuset->effective_mems for a cgroup from another subsystem.

The cs->effective_mems should typically only include online nodes, except during brief transitional
periods such as hotplug operations. Similarly, node migration logic also requires online nodes.

Therefore, cpuset_get_mem_allowed seems acceptable to me.

Additionally, you may consider calling guarantee_online_mems inside your new helper to ensure
consistency.

-- 
Best regards,
Ridong