Re: [RFC PATCH 4/4] mm: Split a slow path for updating mm counters

["David Hildenbrand (Red Hat)" <david@kernel.org>]

On 11/28/25 00:36, Gabriel Krisman Bertazi wrote:
> For cases where we know we are not coming from local context, there is
> no point in touching current when incrementing/decrementing the
> counters.  Split this path into another helper to avoid this cost.
> 
> Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
> ---
>   arch/s390/mm/gmap_helpers.c |  4 ++--
>   arch/s390/mm/pgtable.c      |  4 ++--
>   fs/exec.c                   |  2 +-
>   include/linux/mm.h          | 14 +++++++++++---
>   kernel/events/uprobes.c     |  2 +-
>   mm/filemap.c                |  2 +-
>   mm/huge_memory.c            | 22 +++++++++++-----------
>   mm/khugepaged.c             |  6 +++---
>   mm/ksm.c                    |  2 +-
>   mm/madvise.c                |  2 +-
>   mm/memory.c                 | 20 ++++++++++----------
>   mm/migrate.c                |  2 +-
>   mm/migrate_device.c         |  2 +-
>   mm/rmap.c                   | 16 ++++++++--------
>   mm/swapfile.c               |  6 +++---
>   mm/userfaultfd.c            |  2 +-
>   16 files changed, 58 insertions(+), 50 deletions(-)
> 
> diff --git a/arch/s390/mm/gmap_helpers.c b/arch/s390/mm/gmap_helpers.c
> index d4c3c36855e2..6d8498c56d08 100644
> --- a/arch/s390/mm/gmap_helpers.c
> +++ b/arch/s390/mm/gmap_helpers.c
> @@ -29,9 +29,9 @@
>   static void ptep_zap_swap_entry(struct mm_struct *mm, swp_entry_t entry)
>   {
>   	if (!non_swap_entry(entry))
> -		dec_mm_counter(mm, MM_SWAPENTS);
> +		dec_mm_counter_other(mm, MM_SWAPENTS);
>   	else if (is_migration_entry(entry))
> -		dec_mm_counter(mm, mm_counter(pfn_swap_entry_folio(entry)));
> +		dec_mm_counter_other(mm, mm_counter(pfn_swap_entry_folio(entry)));
>   	free_swap_and_cache(entry);
>   }
>   
> diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
> index 0fde20bbc50b..021a04f958e5 100644
> --- a/arch/s390/mm/pgtable.c
> +++ b/arch/s390/mm/pgtable.c
> @@ -686,11 +686,11 @@ void ptep_unshadow_pte(struct mm_struct *mm, unsigned long saddr, pte_t *ptep)
>   static void ptep_zap_swap_entry(struct mm_struct *mm, swp_entry_t entry)
>   {
>   	if (!non_swap_entry(entry))
> -		dec_mm_counter(mm, MM_SWAPENTS);
> +		dec_mm_counter_other(mm, MM_SWAPENTS);
>   	else if (is_migration_entry(entry)) {
>   		struct folio *folio = pfn_swap_entry_folio(entry);
>   
> -		dec_mm_counter(mm, mm_counter(folio));
> +		dec_mm_counter_other(mm, mm_counter(folio));
>   	}
>   	free_swap_and_cache(entry);
>   }
> diff --git a/fs/exec.c b/fs/exec.c
> index 4298e7e08d5d..33d0eb00d315 100644
> --- a/fs/exec.c
> +++ b/fs/exec.c
> @@ -137,7 +137,7 @@ static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages)
>   		return;
>   
>   	bprm->vma_pages = pages;
> -	add_mm_counter(mm, MM_ANONPAGES, diff);
> +	add_mm_counter_local(mm, MM_ANONPAGES, diff);
>   }
>   
>   static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 29de4c60ac6c..2db12280e938 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -2689,7 +2689,7 @@ static inline unsigned long get_mm_counter_sum(struct mm_struct *mm, int member)
>   
>   void mm_trace_rss_stat(struct mm_struct *mm, int member);
>   
> -static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
> +static inline void add_mm_counter_local(struct mm_struct *mm, int member, long value)
>   {
>   	if (READ_ONCE(current->mm) == mm)
>   		lazy_percpu_counter_add_fast(&mm->rss_stat[member], value);
> @@ -2698,9 +2698,17 @@ static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
>   
>   	mm_trace_rss_stat(mm, member);
>   }
> +static inline void add_mm_counter_other(struct mm_struct *mm, int member, long value)
> +{
> +	lazy_percpu_counter_add_atomic(&mm->rss_stat[member], value);
> +
> +	mm_trace_rss_stat(mm, member);
> +}
>   
> -#define inc_mm_counter(mm, member) add_mm_counter(mm, member, 1)
> -#define dec_mm_counter(mm, member) add_mm_counter(mm, member, -1)
> +#define inc_mm_counter_local(mm, member) add_mm_counter_local(mm, member, 1)
> +#define dec_mm_counter_local(mm, member) add_mm_counter_local(mm, member, -1)
> +#define inc_mm_counter_other(mm, member) add_mm_counter_other(mm, member, 1)
> +#define dec_mm_counter_other(mm, member) add_mm_counter_other(mm, member, -1)

I'd have thought that there is a local and !local version, whereby the 
latter one would simply maintain the old name. The "_other()" sticks out 
a bit.

E.g., cmpxch() vs. cmpxchg_local().

Or would "_remote()" better describe what "_other()" intends to do?

-- 
Cheers

David