Re: [PATCH v9 13/14] khugepaged: add per-order mTHP khugepaged stats

[Baolin Wang <baolin.wang@linux.alibaba.com>]

On 2025/7/14 08:32, Nico Pache wrote:
> With mTHP support inplace, let add the per-order mTHP stats for
> exceeding NONE, SWAP, and SHARED.
> 
> Signed-off-by: Nico Pache <npache@redhat.com>
> ---
>   Documentation/admin-guide/mm/transhuge.rst | 17 +++++++++++++++++
>   include/linux/huge_mm.h                    |  3 +++
>   mm/huge_memory.c                           |  7 +++++++
>   mm/khugepaged.c                            | 15 ++++++++++++---
>   4 files changed, 39 insertions(+), 3 deletions(-)
> 
> diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
> index 2c523dce6bc7..28c8af61efba 100644
> --- a/Documentation/admin-guide/mm/transhuge.rst
> +++ b/Documentation/admin-guide/mm/transhuge.rst
> @@ -658,6 +658,23 @@ nr_anon_partially_mapped
>          an anonymous THP as "partially mapped" and count it here, even though it
>          is not actually partially mapped anymore.
>   
> +collapse_exceed_swap_pte
> +       The number of anonymous THP which contain at least one swap PTE.
> +       Currently khugepaged does not support collapsing mTHP regions that
> +       contain a swap PTE.
> +
> +collapse_exceed_none_pte
> +       The number of anonymous THP which have exceeded the none PTE threshold.
> +       With mTHP collapse, a bitmap is used to gather the state of a PMD region
> +       and is then recursively checked from largest to smallest order against
> +       the scaled max_ptes_none count. This counter indicates that the next
> +       enabled order will be checked.
> +
> +collapse_exceed_shared_pte
> +       The number of anonymous THP which contain at least one shared PTE.
> +       Currently khugepaged does not support collapsing mTHP regions that
> +       contain a shared PTE.
> +
>   As the system ages, allocating huge pages may be expensive as the
>   system uses memory compaction to copy data around memory to free a
>   huge page for use. There are some counters in ``/proc/vmstat`` to help
> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
> index 4042078e8cc9..e0a27f80f390 100644
> --- a/include/linux/huge_mm.h
> +++ b/include/linux/huge_mm.h
> @@ -141,6 +141,9 @@ enum mthp_stat_item {
>   	MTHP_STAT_SPLIT_DEFERRED,
>   	MTHP_STAT_NR_ANON,
>   	MTHP_STAT_NR_ANON_PARTIALLY_MAPPED,
> +	MTHP_STAT_COLLAPSE_EXCEED_SWAP,
> +	MTHP_STAT_COLLAPSE_EXCEED_NONE,
> +	MTHP_STAT_COLLAPSE_EXCEED_SHARED,
>   	__MTHP_STAT_COUNT
>   };
>   
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index e2ed9493df77..57e5699cf638 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -632,6 +632,10 @@ DEFINE_MTHP_STAT_ATTR(split_failed, MTHP_STAT_SPLIT_FAILED);
>   DEFINE_MTHP_STAT_ATTR(split_deferred, MTHP_STAT_SPLIT_DEFERRED);
>   DEFINE_MTHP_STAT_ATTR(nr_anon, MTHP_STAT_NR_ANON);
>   DEFINE_MTHP_STAT_ATTR(nr_anon_partially_mapped, MTHP_STAT_NR_ANON_PARTIALLY_MAPPED);
> +DEFINE_MTHP_STAT_ATTR(collapse_exceed_swap_pte, MTHP_STAT_COLLAPSE_EXCEED_SWAP);
> +DEFINE_MTHP_STAT_ATTR(collapse_exceed_none_pte, MTHP_STAT_COLLAPSE_EXCEED_NONE);
> +DEFINE_MTHP_STAT_ATTR(collapse_exceed_shared_pte, MTHP_STAT_COLLAPSE_EXCEED_SHARED);
> +
>   
>   static struct attribute *anon_stats_attrs[] = {
>   	&anon_fault_alloc_attr.attr,
> @@ -648,6 +652,9 @@ static struct attribute *anon_stats_attrs[] = {
>   	&split_deferred_attr.attr,
>   	&nr_anon_attr.attr,
>   	&nr_anon_partially_mapped_attr.attr,
> +	&collapse_exceed_swap_pte_attr.attr,
> +	&collapse_exceed_none_pte_attr.attr,
> +	&collapse_exceed_shared_pte_attr.attr,
>   	NULL,
>   };
>   
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index d0c99b86b304..8a5873d0a23a 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -594,7 +594,10 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
>   				continue;
>   			} else {
>   				result = SCAN_EXCEED_NONE_PTE;
> -				count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
> +				if (order == HPAGE_PMD_ORDER)
> +					count_vm_event(THP_SCAN_EXCEED_NONE_PTE);
> +				else
> +					count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_NONE);

Please follow the same logic as other mTHP statistics, meaning there is 
no need to filter out PMD-sized orders, because mTHP also supports 
PMD-sized orders. So logic should be:

if (order == HPAGE_PMD_ORDER)
	count_vm_event(THP_SCAN_EXCEED_NONE_PTE);

count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_NONE);

>   				goto out;
>   			}
>   		}
> @@ -623,8 +626,14 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
>   		/* See khugepaged_scan_pmd(). */
>   		if (folio_maybe_mapped_shared(folio)) {
>   			++shared;
> -			if (order != HPAGE_PMD_ORDER || (cc->is_khugepaged &&
> -			    shared > khugepaged_max_ptes_shared)) {
> +			if (order != HPAGE_PMD_ORDER) {
> +				result = SCAN_EXCEED_SHARED_PTE;
> +				count_mthp_stat(order, MTHP_STAT_COLLAPSE_EXCEED_SHARED);
> +				goto out;
> +			}

Ditto.

> +
> +			if (cc->is_khugepaged &&
> +				shared > khugepaged_max_ptes_shared) {
>   				result = SCAN_EXCEED_SHARED_PTE;
>   				count_vm_event(THP_SCAN_EXCEED_SHARED_PTE);
>   				goto out;