diff mbox series

[RFC,2/6] mm: memcg: make memcg huge page split support any order split.

Message ID 20201111204008.21332-3-zi.yan@sent.com (mailing list archive)
State New, archived
Headers show
Series Split huge pages to any lower order pages. | expand

Commit Message

Zi Yan Nov. 11, 2020, 8:40 p.m. UTC 
From: Zi Yan <ziy@nvidia.com>

It reads thp_nr_pages and splits to provided new_nr. It prepares for
upcoming changes to support split huge page to any lower order.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 include/linux/memcontrol.h | 5 +++--
 mm/huge_memory.c           | 2 +-
 mm/memcontrol.c            | 4 ++--
 3 files changed, 6 insertions(+), 5 deletions(-)

Comments

Ralph Campbell Nov. 12, 2020, 5:58 p.m. UTC | #1 
On 11/11/20 12:40 PM, Zi Yan wrote:
> From: Zi Yan <ziy@nvidia.com>
> 
> It reads thp_nr_pages and splits to provided new_nr. It prepares for
> upcoming changes to support split huge page to any lower order.
> 
> Signed-off-by: Zi Yan <ziy@nvidia.com>

Looks OK to me.
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>

> ---
>   include/linux/memcontrol.h | 5 +++--
>   mm/huge_memory.c           | 2 +-
>   mm/memcontrol.c            | 4 ++--
>   3 files changed, 6 insertions(+), 5 deletions(-)
> 
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 0f4dd7829fb2..b3bac79ceed6 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -1105,7 +1105,7 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
>   }
>   
>   #ifdef CONFIG_TRANSPARENT_HUGEPAGE
> -void mem_cgroup_split_huge_fixup(struct page *head);
> +void mem_cgroup_split_huge_fixup(struct page *head, unsigned int new_nr);
>   #endif
>   
>   #else /* CONFIG_MEMCG */
> @@ -1451,7 +1451,8 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
>   	return 0;
>   }
>   
> -static inline void mem_cgroup_split_huge_fixup(struct page *head)
> +static inline void mem_cgroup_split_huge_fixup(struct page *head,
> +					       unsigned int new_nr)
>   {
>   }
>   
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index c4fead5ead31..f599f5b9bf7f 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -2429,7 +2429,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
>   	lruvec = mem_cgroup_page_lruvec(head, pgdat);
>   
>   	/* complete memcg works before add pages to LRU */
> -	mem_cgroup_split_huge_fixup(head);
> +	mem_cgroup_split_huge_fixup(head, 1);
>   
>   	if (PageAnon(head) && PageSwapCache(head)) {
>   		swp_entry_t entry = { .val = page_private(head) };
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 33f632689cee..e9705ba6bbcc 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -3247,7 +3247,7 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
>    * Because tail pages are not marked as "used", set it. We're under
>    * pgdat->lru_lock and migration entries setup in all page mappings.
>    */
> -void mem_cgroup_split_huge_fixup(struct page *head)
> +void mem_cgroup_split_huge_fixup(struct page *head, unsigned int new_nr)
>   {
>   	struct mem_cgroup *memcg = page_memcg(head);
>   	int i;
> @@ -3255,7 +3255,7 @@ void mem_cgroup_split_huge_fixup(struct page *head)
>   	if (mem_cgroup_disabled())
>   		return;
>   
> -	for (i = 1; i < thp_nr_pages(head); i++) {
> +	for (i = new_nr; i < thp_nr_pages(head); i += new_nr) {
>   		css_get(&memcg->css);
>   		head[i].memcg_data = (unsigned long)memcg;
>   	}
>
Zi Yan Nov. 12, 2020, 6 p.m. UTC | #2 
On 12 Nov 2020, at 12:58, Ralph Campbell wrote:

> On 11/11/20 12:40 PM, Zi Yan wrote:
>> From: Zi Yan <ziy@nvidia.com>
>>
>> It reads thp_nr_pages and splits to provided new_nr. It prepares for
>> upcoming changes to support split huge page to any lower order.
>>
>> Signed-off-by: Zi Yan <ziy@nvidia.com>
>
> Looks OK to me.
> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>

Thanks.

—
Best Regards,
Yan Zi
Roman Gushchin Nov. 14, 2020, 12:23 a.m. UTC | #3 
On Wed, Nov 11, 2020 at 03:40:04PM -0500, Zi Yan wrote:
> From: Zi Yan <ziy@nvidia.com>
> 
> It reads thp_nr_pages and splits to provided new_nr. It prepares for
> upcoming changes to support split huge page to any lower order.
> 
> Signed-off-by: Zi Yan <ziy@nvidia.com>
> ---
>  include/linux/memcontrol.h | 5 +++--
>  mm/huge_memory.c           | 2 +-
>  mm/memcontrol.c            | 4 ++--
>  3 files changed, 6 insertions(+), 5 deletions(-)
> 
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 0f4dd7829fb2..b3bac79ceed6 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -1105,7 +1105,7 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
>  }
>  
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
> -void mem_cgroup_split_huge_fixup(struct page *head);
> +void mem_cgroup_split_huge_fixup(struct page *head, unsigned int new_nr);
>  #endif
>  
>  #else /* CONFIG_MEMCG */
> @@ -1451,7 +1451,8 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
>  	return 0;
>  }
>  
> -static inline void mem_cgroup_split_huge_fixup(struct page *head)
> +static inline void mem_cgroup_split_huge_fixup(struct page *head,
> +					       unsigned int new_nr)
>  {
>  }
>  
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index c4fead5ead31..f599f5b9bf7f 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -2429,7 +2429,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
>  	lruvec = mem_cgroup_page_lruvec(head, pgdat);
>  
>  	/* complete memcg works before add pages to LRU */
> -	mem_cgroup_split_huge_fixup(head);
> +	mem_cgroup_split_huge_fixup(head, 1);
>  
>  	if (PageAnon(head) && PageSwapCache(head)) {
>  		swp_entry_t entry = { .val = page_private(head) };
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 33f632689cee..e9705ba6bbcc 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -3247,7 +3247,7 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
>   * Because tail pages are not marked as "used", set it. We're under
>   * pgdat->lru_lock and migration entries setup in all page mappings.
>   */
> -void mem_cgroup_split_huge_fixup(struct page *head)
> +void mem_cgroup_split_huge_fixup(struct page *head, unsigned int new_nr)

I'd go with unsigned int new_order, then it's obvious that we can split
the original page without any leftovers.

Other than that the patch looks good!
Acked-by: Roman Gushchin <guro@fb.com>

Thanks!

>  {
>  	struct mem_cgroup *memcg = page_memcg(head);
>  	int i;
> @@ -3255,7 +3255,7 @@ void mem_cgroup_split_huge_fixup(struct page *head)
>  	if (mem_cgroup_disabled())
>  		return;
>  
> -	for (i = 1; i < thp_nr_pages(head); i++) {
> +	for (i = new_nr; i < thp_nr_pages(head); i += new_nr) {
>  		css_get(&memcg->css);
>  		head[i].memcg_data = (unsigned long)memcg;
>  	}
> -- 
> 2.28.0
>
Zi Yan Nov. 14, 2020, 12:56 a.m. UTC | #4 
On 13 Nov 2020, at 19:23, Roman Gushchin wrote:

> On Wed, Nov 11, 2020 at 03:40:04PM -0500, Zi Yan wrote:
>> From: Zi Yan <ziy@nvidia.com>
>>
>> It reads thp_nr_pages and splits to provided new_nr. It prepares for
>> upcoming changes to support split huge page to any lower order.
>>
>> Signed-off-by: Zi Yan <ziy@nvidia.com>
>> ---
>>  include/linux/memcontrol.h | 5 +++--
>>  mm/huge_memory.c           | 2 +-
>>  mm/memcontrol.c            | 4 ++--
>>  3 files changed, 6 insertions(+), 5 deletions(-)
>>
>> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
>> index 0f4dd7829fb2..b3bac79ceed6 100644
>> --- a/include/linux/memcontrol.h
>> +++ b/include/linux/memcontrol.h
>> @@ -1105,7 +1105,7 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
>>  }
>>
>>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>> -void mem_cgroup_split_huge_fixup(struct page *head);
>> +void mem_cgroup_split_huge_fixup(struct page *head, unsigned int new_nr);
>>  #endif
>>
>>  #else /* CONFIG_MEMCG */
>> @@ -1451,7 +1451,8 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
>>  	return 0;
>>  }
>>
>> -static inline void mem_cgroup_split_huge_fixup(struct page *head)
>> +static inline void mem_cgroup_split_huge_fixup(struct page *head,
>> +					       unsigned int new_nr)
>>  {
>>  }
>>
>> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
>> index c4fead5ead31..f599f5b9bf7f 100644
>> --- a/mm/huge_memory.c
>> +++ b/mm/huge_memory.c
>> @@ -2429,7 +2429,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
>>  	lruvec = mem_cgroup_page_lruvec(head, pgdat);
>>
>>  	/* complete memcg works before add pages to LRU */
>> -	mem_cgroup_split_huge_fixup(head);
>> +	mem_cgroup_split_huge_fixup(head, 1);
>>
>>  	if (PageAnon(head) && PageSwapCache(head)) {
>>  		swp_entry_t entry = { .val = page_private(head) };
>> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
>> index 33f632689cee..e9705ba6bbcc 100644
>> --- a/mm/memcontrol.c
>> +++ b/mm/memcontrol.c
>> @@ -3247,7 +3247,7 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
>>   * Because tail pages are not marked as "used", set it. We're under
>>   * pgdat->lru_lock and migration entries setup in all page mappings.
>>   */
>> -void mem_cgroup_split_huge_fixup(struct page *head)
>> +void mem_cgroup_split_huge_fixup(struct page *head, unsigned int new_nr)
>
> I'd go with unsigned int new_order, then it's obvious that we can split
> the original page without any leftovers.

Makes sense. Will change it.

>
> Other than that the patch looks good!
> Acked-by: Roman Gushchin <guro@fb.com>

Thanks.

>>  {
>>  	struct mem_cgroup *memcg = page_memcg(head);
>>  	int i;
>> @@ -3255,7 +3255,7 @@ void mem_cgroup_split_huge_fixup(struct page *head)
>>  	if (mem_cgroup_disabled())
>>  		return;
>>
>> -	for (i = 1; i < thp_nr_pages(head); i++) {
>> +	for (i = new_nr; i < thp_nr_pages(head); i += new_nr) {
>>  		css_get(&memcg->css);
>>  		head[i].memcg_data = (unsigned long)memcg;
>>  	}
>> -- 
>> 2.28.0
>>


—
Best Regards,
Yan Zi
diff mbox series

Patch

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 0f4dd7829fb2..b3bac79ceed6 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1105,7 +1105,7 @@  static inline void memcg_memory_event_mm(struct mm_struct *mm,
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-void mem_cgroup_split_huge_fixup(struct page *head);
+void mem_cgroup_split_huge_fixup(struct page *head, unsigned int new_nr);
 #endif
 
 #else /* CONFIG_MEMCG */
@@ -1451,7 +1451,8 @@  unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 	return 0;
 }
 
-static inline void mem_cgroup_split_huge_fixup(struct page *head)
+static inline void mem_cgroup_split_huge_fixup(struct page *head,
+					       unsigned int new_nr)
 {
 }
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c4fead5ead31..f599f5b9bf7f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2429,7 +2429,7 @@  static void __split_huge_page(struct page *page, struct list_head *list,
 	lruvec = mem_cgroup_page_lruvec(head, pgdat);
 
 	/* complete memcg works before add pages to LRU */
-	mem_cgroup_split_huge_fixup(head);
+	mem_cgroup_split_huge_fixup(head, 1);
 
 	if (PageAnon(head) && PageSwapCache(head)) {
 		swp_entry_t entry = { .val = page_private(head) };
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 33f632689cee..e9705ba6bbcc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3247,7 +3247,7 @@  void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
  * Because tail pages are not marked as "used", set it. We're under
  * pgdat->lru_lock and migration entries setup in all page mappings.
  */
-void mem_cgroup_split_huge_fixup(struct page *head)
+void mem_cgroup_split_huge_fixup(struct page *head, unsigned int new_nr)
 {
 	struct mem_cgroup *memcg = page_memcg(head);
 	int i;
@@ -3255,7 +3255,7 @@  void mem_cgroup_split_huge_fixup(struct page *head)
 	if (mem_cgroup_disabled())
 		return;
 
-	for (i = 1; i < thp_nr_pages(head); i++) {
+	for (i = new_nr; i < thp_nr_pages(head); i += new_nr) {
 		css_get(&memcg->css);
 		head[i].memcg_data = (unsigned long)memcg;
 	}