[PATCH v9 04/14] khugepaged: generalize alloc_charge_folio()

Nico Pache posted 14 patches 2 months, 3 weeks ago
There is a newer version of this series
[PATCH v9 04/14] khugepaged: generalize alloc_charge_folio()
Posted by Nico Pache 2 months, 3 weeks ago
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>
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>
---
 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 dff8d5985f0f..2c523dce6bc7 100644
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -583,6 +583,14 @@ 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 7748489fde1b..4042078e8cc9 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -125,6 +125,8 @@ 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 bd7a623d7ef8..e2ed9493df77 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -614,6 +614,8 @@ 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);
@@ -679,6 +681,8 @@ 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 fa0642e66790..cc9a35185604 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1068,21 +1068,26 @@ 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, u8 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;
@@ -1119,7 +1124,7 @@ 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;
 
@@ -1843,7 +1848,7 @@ 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;
 
-- 
2.50.0
Re: [PATCH v9 04/14] khugepaged: generalize alloc_charge_folio()
Posted by David Hildenbrand 2 months, 3 weeks ago
On 14.07.25 02:31, 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>
> 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>
> ---
>   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 dff8d5985f0f..2c523dce6bc7 100644
> --- a/Documentation/admin-guide/mm/transhuge.rst
> +++ b/Documentation/admin-guide/mm/transhuge.rst
> @@ -583,6 +583,14 @@ 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 7748489fde1b..4042078e8cc9 100644
> --- a/include/linux/huge_mm.h
> +++ b/include/linux/huge_mm.h
> @@ -125,6 +125,8 @@ 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 bd7a623d7ef8..e2ed9493df77 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -614,6 +614,8 @@ 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);
> @@ -679,6 +681,8 @@ 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 fa0642e66790..cc9a35185604 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -1068,21 +1068,26 @@ 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, u8 order)

u8, really? :)

Just use an "unsigned int" like folio_order() would or what 
__folio_alloc() consumes.



Apart from that

Acked-by: David Hildenbrand <david@redhat.com>

-- 
Cheers,

David / dhildenb
Re: [PATCH v9 04/14] khugepaged: generalize alloc_charge_folio()
Posted by Nico Pache 2 months, 3 weeks ago
On Wed, Jul 16, 2025 at 7:46 AM David Hildenbrand <david@redhat.com> wrote:
>
> On 14.07.25 02:31, 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>
> > 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>
> > ---
> >   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 dff8d5985f0f..2c523dce6bc7 100644
> > --- a/Documentation/admin-guide/mm/transhuge.rst
> > +++ b/Documentation/admin-guide/mm/transhuge.rst
> > @@ -583,6 +583,14 @@ 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 7748489fde1b..4042078e8cc9 100644
> > --- a/include/linux/huge_mm.h
> > +++ b/include/linux/huge_mm.h
> > @@ -125,6 +125,8 @@ 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 bd7a623d7ef8..e2ed9493df77 100644
> > --- a/mm/huge_memory.c
> > +++ b/mm/huge_memory.c
> > @@ -614,6 +614,8 @@ 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);
> > @@ -679,6 +681,8 @@ 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 fa0642e66790..cc9a35185604 100644
> > --- a/mm/khugepaged.c
> > +++ b/mm/khugepaged.c
> > @@ -1068,21 +1068,26 @@ 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, u8 order)
>
> u8, really? :)
At the time I knew I was going to use u8's at the bitmap level so I
thought I should have them here too. But you are right I went through
and cleaned up all the u8 usage with the exception of the actual
bitmap storage.
>
> Just use an "unsigned int" like folio_order() would or what
> __folio_alloc() consumes.
>
>
>
> Apart from that
>
> Acked-by: David Hildenbrand <david@redhat.com>
Thank you!

>
> --
> Cheers,
>
> David / dhildenb
>