On 2025/10/23 02:37, Nico Pache wrote:
> From: Dev Jain <dev.jain@arm.com>
>
> Pass order to alloc_charge_folio() and update mTHP statistics.
>
> Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
> Acked-by: David Hildenbrand <david@redhat.com>
> Co-developed-by: Nico Pache <npache@redhat.com>
> Signed-off-by: Nico Pache <npache@redhat.com>
> Signed-off-by: Dev Jain <dev.jain@arm.com>
> ---
Cool! LGTM.
Reviewed-by: Lance Yang <lance.yang@linux.dev>
> Documentation/admin-guide/mm/transhuge.rst | 8 ++++++++
> include/linux/huge_mm.h | 2 ++
> mm/huge_memory.c | 4 ++++
> mm/khugepaged.c | 17 +++++++++++------
> 4 files changed, 25 insertions(+), 6 deletions(-)
>
> diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
> index 1654211cc6cf..13269a0074d4 100644
> --- a/Documentation/admin-guide/mm/transhuge.rst
> +++ b/Documentation/admin-guide/mm/transhuge.rst
> @@ -634,6 +634,14 @@ anon_fault_fallback_charge
> instead falls back to using huge pages with lower orders or
> small pages even though the allocation was successful.
>
> +collapse_alloc
> + is incremented every time a huge page is successfully allocated for a
> + khugepaged collapse.
> +
> +collapse_alloc_failed
> + is incremented every time a huge page allocation fails during a
> + khugepaged collapse.
> +
> zswpout
> is incremented every time a huge page is swapped out to zswap in one
> piece without splitting.
> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
> index 7698b3542c4f..3d29624c4f3f 100644
> --- a/include/linux/huge_mm.h
> +++ b/include/linux/huge_mm.h
> @@ -128,6 +128,8 @@ enum mthp_stat_item {
> MTHP_STAT_ANON_FAULT_ALLOC,
> MTHP_STAT_ANON_FAULT_FALLBACK,
> MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE,
> + MTHP_STAT_COLLAPSE_ALLOC,
> + MTHP_STAT_COLLAPSE_ALLOC_FAILED,
> MTHP_STAT_ZSWPOUT,
> MTHP_STAT_SWPIN,
> MTHP_STAT_SWPIN_FALLBACK,
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 370ecfd6a182..0063d1ba926e 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -620,6 +620,8 @@ static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
> DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC);
> DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK);
> DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
> +DEFINE_MTHP_STAT_ATTR(collapse_alloc, MTHP_STAT_COLLAPSE_ALLOC);
> +DEFINE_MTHP_STAT_ATTR(collapse_alloc_failed, MTHP_STAT_COLLAPSE_ALLOC_FAILED);
> DEFINE_MTHP_STAT_ATTR(zswpout, MTHP_STAT_ZSWPOUT);
> DEFINE_MTHP_STAT_ATTR(swpin, MTHP_STAT_SWPIN);
> DEFINE_MTHP_STAT_ATTR(swpin_fallback, MTHP_STAT_SWPIN_FALLBACK);
> @@ -685,6 +687,8 @@ static struct attribute *any_stats_attrs[] = {
> #endif
> &split_attr.attr,
> &split_failed_attr.attr,
> + &collapse_alloc_attr.attr,
> + &collapse_alloc_failed_attr.attr,
> NULL,
> };
>
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index 6cf8700823f9..36ee659acfbb 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -1061,21 +1061,26 @@ static int __collapse_huge_page_swapin(struct mm_struct *mm,
> }
>
> static int alloc_charge_folio(struct folio **foliop, struct mm_struct *mm,
> - struct collapse_control *cc)
> + struct collapse_control *cc, unsigned int order)
> {
> gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() :
> GFP_TRANSHUGE);
> int node = collapse_find_target_node(cc);
> struct folio *folio;
>
> - folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, &cc->alloc_nmask);
> + folio = __folio_alloc(gfp, order, node, &cc->alloc_nmask);
> if (!folio) {
> *foliop = NULL;
> - count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
> + if (order == HPAGE_PMD_ORDER)
> + count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
> + count_mthp_stat(order, MTHP_STAT_COLLAPSE_ALLOC_FAILED);
> return SCAN_ALLOC_HUGE_PAGE_FAIL;
> }
>
> - count_vm_event(THP_COLLAPSE_ALLOC);
> + if (order == HPAGE_PMD_ORDER)
> + count_vm_event(THP_COLLAPSE_ALLOC);
> + count_mthp_stat(order, MTHP_STAT_COLLAPSE_ALLOC);
> +
> if (unlikely(mem_cgroup_charge(folio, mm, gfp))) {
> folio_put(folio);
> *foliop = NULL;
> @@ -1112,7 +1117,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address,
> */
> mmap_read_unlock(mm);
>
> - result = alloc_charge_folio(&folio, mm, cc);
> + result = alloc_charge_folio(&folio, mm, cc, HPAGE_PMD_ORDER);
> if (result != SCAN_SUCCEED)
> goto out_nolock;
>
> @@ -1850,7 +1855,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
> VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem);
> VM_BUG_ON(start & (HPAGE_PMD_NR - 1));
>
> - result = alloc_charge_folio(&new_folio, mm, cc);
> + result = alloc_charge_folio(&new_folio, mm, cc, HPAGE_PMD_ORDER);
> if (result != SCAN_SUCCEED)
> goto out;
>