From: Chen Ridong <chenridong@huawei.com>
The mem_cgroup_size helper is used only in apply_proportional_protection
to read the current memory usage. Its semantics are unclear and
inconsistent with other sites, which directly call page_counter_read for
the same purpose.
Remove this helper and replace its usage with page_counter_read for
clarity. Additionally, rename the local variable 'cgroup_size' to 'usage'
to better reflect its meaning.
This change is safe because page_counter_read() is only called when memcg
is enabled in the apply_proportional_protection.
No functional changes intended.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
---
include/linux/memcontrol.h | 7 -------
mm/memcontrol.c | 5 -----
mm/vmscan.c | 8 +++++---
3 files changed, 5 insertions(+), 15 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6a48398a1f4e..bedeb606c691 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -919,8 +919,6 @@ static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask)
unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg);
-unsigned long mem_cgroup_size(struct mem_cgroup *memcg);
-
void mem_cgroup_print_oom_context(struct mem_cgroup *memcg,
struct task_struct *p);
@@ -1328,11 +1326,6 @@ static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
return 0;
}
-static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg)
-{
- return 0;
-}
-
static inline void
mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p)
{
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index dbe7d8f93072..659ce171b1b3 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1621,11 +1621,6 @@ unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
return max;
}
-unsigned long mem_cgroup_size(struct mem_cgroup *memcg)
-{
- return page_counter_read(&memcg->memory);
-}
-
void __memcg_memory_event(struct mem_cgroup *memcg,
enum memcg_memory_event event, bool allow_spinning)
{
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 670fe9fae5ba..fe48d0376e7c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2451,6 +2451,7 @@ static inline void calculate_pressure_balance(struct scan_control *sc,
static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
struct scan_control *sc, unsigned long scan)
{
+#ifdef CONFIG_MEMCG
unsigned long min, low;
mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low);
@@ -2485,7 +2486,7 @@ static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
* again by how much of the total memory used is under
* hard protection.
*/
- unsigned long cgroup_size = mem_cgroup_size(memcg);
+ unsigned long usage = page_counter_read(&memcg->memory);
unsigned long protection;
/* memory.low scaling, make sure we retry before OOM */
@@ -2497,9 +2498,9 @@ static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
}
/* Avoid TOCTOU with earlier protection check */
- cgroup_size = max(cgroup_size, protection);
+ usage = max(usage, protection);
- scan -= scan * protection / (cgroup_size + 1);
+ scan -= scan * protection / (usage + 1);
/*
* Minimally target SWAP_CLUSTER_MAX pages to keep
@@ -2508,6 +2509,7 @@ static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
*/
scan = max(scan, SWAP_CLUSTER_MAX);
}
+#endif
return scan;
}
--
2.34.1
On Wed, Dec 10, 2025 at 07:11:42AM +0000, Chen Ridong wrote:
> From: Chen Ridong <chenridong@huawei.com>
>
> The mem_cgroup_size helper is used only in apply_proportional_protection
> to read the current memory usage. Its semantics are unclear and
> inconsistent with other sites, which directly call page_counter_read for
> the same purpose.
>
> Remove this helper and replace its usage with page_counter_read for
> clarity. Additionally, rename the local variable 'cgroup_size' to 'usage'
> to better reflect its meaning.
+1
I don't think the helper adds much.
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2451,6 +2451,7 @@ static inline void calculate_pressure_balance(struct scan_control *sc,
> static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
> struct scan_control *sc, unsigned long scan)
> {
> +#ifdef CONFIG_MEMCG
> unsigned long min, low;
>
> mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low);
> @@ -2485,7 +2486,7 @@ static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
> * again by how much of the total memory used is under
> * hard protection.
> */
> - unsigned long cgroup_size = mem_cgroup_size(memcg);
> + unsigned long usage = page_counter_read(&memcg->memory);
> unsigned long protection;
>
> /* memory.low scaling, make sure we retry before OOM */
> @@ -2497,9 +2498,9 @@ static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
> }
>
> /* Avoid TOCTOU with earlier protection check */
> - cgroup_size = max(cgroup_size, protection);
> + usage = max(usage, protection);
>
> - scan -= scan * protection / (cgroup_size + 1);
> + scan -= scan * protection / (usage + 1);
>
> /*
> * Minimally target SWAP_CLUSTER_MAX pages to keep
> @@ -2508,6 +2509,7 @@ static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
> */
> scan = max(scan, SWAP_CLUSTER_MAX);
> }
> +#endif
To avoid the ifdef, how about making it
bool mem_cgroup_protection(root, memcg, &min, &low, &usage)
and branch the scaling on that return value. The compiler should be
able to eliminate the entire branch in the !CONFIG_MEMCG case. And it
keeps a cleaner split between memcg logic and reclaim logic.
On 2025/12/11 0:36, Johannes Weiner wrote:
> On Wed, Dec 10, 2025 at 07:11:42AM +0000, Chen Ridong wrote:
>> From: Chen Ridong <chenridong@huawei.com>
>>
>> The mem_cgroup_size helper is used only in apply_proportional_protection
>> to read the current memory usage. Its semantics are unclear and
>> inconsistent with other sites, which directly call page_counter_read for
>> the same purpose.
>>
>> Remove this helper and replace its usage with page_counter_read for
>> clarity. Additionally, rename the local variable 'cgroup_size' to 'usage'
>> to better reflect its meaning.
>
> +1
>
> I don't think the helper adds much.
>
>> --- a/mm/vmscan.c
>> +++ b/mm/vmscan.c
>> @@ -2451,6 +2451,7 @@ static inline void calculate_pressure_balance(struct scan_control *sc,
>> static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
>> struct scan_control *sc, unsigned long scan)
>> {
>> +#ifdef CONFIG_MEMCG
>> unsigned long min, low;
>>
>> mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low);
>> @@ -2485,7 +2486,7 @@ static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
>> * again by how much of the total memory used is under
>> * hard protection.
>> */
>> - unsigned long cgroup_size = mem_cgroup_size(memcg);
>> + unsigned long usage = page_counter_read(&memcg->memory);
>> unsigned long protection;
>>
>> /* memory.low scaling, make sure we retry before OOM */
>> @@ -2497,9 +2498,9 @@ static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
>> }
>>
>> /* Avoid TOCTOU with earlier protection check */
>> - cgroup_size = max(cgroup_size, protection);
>> + usage = max(usage, protection);
>>
>> - scan -= scan * protection / (cgroup_size + 1);
>> + scan -= scan * protection / (usage + 1);
>>
>> /*
>> * Minimally target SWAP_CLUSTER_MAX pages to keep
>> @@ -2508,6 +2509,7 @@ static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
>> */
>> scan = max(scan, SWAP_CLUSTER_MAX);
>> }
>> +#endif
>
> To avoid the ifdef, how about making it
>
> bool mem_cgroup_protection(root, memcg, &min, &low, &usage)
>
> and branch the scaling on that return value. The compiler should be
> able to eliminate the entire branch in the !CONFIG_MEMCG case. And it
> keeps a cleaner split between memcg logic and reclaim logic.
Much better, will update.
--
Best regards,
Ridong
On Wed 10-12-25 07:11:42, Chen Ridong wrote:
> From: Chen Ridong <chenridong@huawei.com>
>
> The mem_cgroup_size helper is used only in apply_proportional_protection
> to read the current memory usage. Its semantics are unclear and
> inconsistent with other sites, which directly call page_counter_read for
> the same purpose.
>
> Remove this helper and replace its usage with page_counter_read for
> clarity. Additionally, rename the local variable 'cgroup_size' to 'usage'
> to better reflect its meaning.
>
> This change is safe because page_counter_read() is only called when memcg
> is enabled in the apply_proportional_protection.
>
> No functional changes intended.
I would prefer to keep the code as is.
Btw.
[...]
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 670fe9fae5ba..fe48d0376e7c 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2451,6 +2451,7 @@ static inline void calculate_pressure_balance(struct scan_control *sc,
> static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
> struct scan_control *sc, unsigned long scan)
> {
> +#ifdef CONFIG_MEMCG
> unsigned long min, low;
>
> mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low);
[...]
> @@ -2508,6 +2509,7 @@ static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
> */
> scan = max(scan, SWAP_CLUSTER_MAX);
> }
> +#endif
> return scan;
> }
This returns a random garbage for !CONFIG_MEMCG, doesn't it?
--
Michal Hocko
SUSE Labs
On 2025/12/10 16:05, Michal Hocko wrote:
> On Wed 10-12-25 07:11:42, Chen Ridong wrote:
>> From: Chen Ridong <chenridong@huawei.com>
>>
>> The mem_cgroup_size helper is used only in apply_proportional_protection
>> to read the current memory usage. Its semantics are unclear and
>> inconsistent with other sites, which directly call page_counter_read for
>> the same purpose.
>>
>> Remove this helper and replace its usage with page_counter_read for
>> clarity. Additionally, rename the local variable 'cgroup_size' to 'usage'
>> to better reflect its meaning.
>>
>> This change is safe because page_counter_read() is only called when memcg
>> is enabled in the apply_proportional_protection.
>>
>> No functional changes intended.
>
> I would prefer to keep the code as is.
>
I find the mem_cgroup_size() function name misleading—it suggests counting the number of memory
cgroups, but it actually returns the current memory usage.
When looking for a clearer alternative, I found mem_cgroup_usage(), which is only called by v1. This
raised the question of whether mem_cgroup_size() is truly necessary. Moreover, I noticed other code
locations simply call page_counter_read() directly to obtain current usage.
> Btw.
> [...]
>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>> index 670fe9fae5ba..fe48d0376e7c 100644
>> --- a/mm/vmscan.c
>> +++ b/mm/vmscan.c
>> @@ -2451,6 +2451,7 @@ static inline void calculate_pressure_balance(struct scan_control *sc,
>> static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
>> struct scan_control *sc, unsigned long scan)
>> {
>> +#ifdef CONFIG_MEMCG
>> unsigned long min, low;
>>
>> mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low);
> [...]
>> @@ -2508,6 +2509,7 @@ static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
>> */
>> scan = max(scan, SWAP_CLUSTER_MAX);
>> }
>> +#endif
>> return scan;
>> }
>
> This returns a random garbage for !CONFIG_MEMCG, doesn't it?
>
--
Best regards,
Ridong
On 2025/12/10 16:05, Michal Hocko wrote:
> On Wed 10-12-25 07:11:42, Chen Ridong wrote:
>> From: Chen Ridong <chenridong@huawei.com>
>>
>> The mem_cgroup_size helper is used only in apply_proportional_protection
>> to read the current memory usage. Its semantics are unclear and
>> inconsistent with other sites, which directly call page_counter_read for
>> the same purpose.
>>
>> Remove this helper and replace its usage with page_counter_read for
>> clarity. Additionally, rename the local variable 'cgroup_size' to 'usage'
>> to better reflect its meaning.
>>
>> This change is safe because page_counter_read() is only called when memcg
>> is enabled in the apply_proportional_protection.
>>
>> No functional changes intended.
>
> I would prefer to keep the code as is.
>
> Btw.
> [...]
>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>> index 670fe9fae5ba..fe48d0376e7c 100644
>> --- a/mm/vmscan.c
>> +++ b/mm/vmscan.c
>> @@ -2451,6 +2451,7 @@ static inline void calculate_pressure_balance(struct scan_control *sc,
>> static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
>> struct scan_control *sc, unsigned long scan)
>> {
>> +#ifdef CONFIG_MEMCG
>> unsigned long min, low;
>>
>> mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low);
> [...]
>> @@ -2508,6 +2509,7 @@ static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
>> */
>> scan = max(scan, SWAP_CLUSTER_MAX);
>> }
>> +#endif
>> return scan;
>> }
>
> This returns a random garbage for !CONFIG_MEMCG, doesn't it?
>
This returns what was passed as input. This means the scan behavior remains unchanged when memcg is
disabled. When memcg is enabled, the scan amount may be proportionally scaled.
--
Best regards,
Ridong
On Wed 10-12-25 16:31:37, Chen Ridong wrote:
>
>
> On 2025/12/10 16:05, Michal Hocko wrote:
[...]
> >> diff --git a/mm/vmscan.c b/mm/vmscan.c
> >> index 670fe9fae5ba..fe48d0376e7c 100644
> >> --- a/mm/vmscan.c
> >> +++ b/mm/vmscan.c
> >> @@ -2451,6 +2451,7 @@ static inline void calculate_pressure_balance(struct scan_control *sc,
> >> static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
> >> struct scan_control *sc, unsigned long scan)
> >> {
> >> +#ifdef CONFIG_MEMCG
> >> unsigned long min, low;
> >>
> >> mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low);
> > [...]
> >> @@ -2508,6 +2509,7 @@ static unsigned long apply_proportional_protection(struct mem_cgroup *memcg,
> >> */
> >> scan = max(scan, SWAP_CLUSTER_MAX);
> >> }
> >> +#endif
> >> return scan;
> >> }
> >
> > This returns a random garbage for !CONFIG_MEMCG, doesn't it?
> >
>
> This returns what was passed as input. This means the scan behavior remains unchanged when memcg is
> disabled. When memcg is enabled, the scan amount may be proportionally scaled.
Right you are. My bad. Sorry for the confusion.
--
Michal Hocko
SUSE Labs
© 2016 - 2025 Red Hat, Inc.