linux-kernel - Re: [PATCH v10 04/13] khugepaged: generalize alloc_charge

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <08cca28e-24b0-4dc9-870e-f328a788a454@lucifer.local>
Date: Wed, 20 Aug 2025 14:28:08 +0100
From: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
To: Nico Pache <npache@...hat.com>
Cc: linux-mm@...ck.org, linux-doc@...r.kernel.org,
        linux-kernel@...r.kernel.org, linux-trace-kernel@...r.kernel.org,
        david@...hat.com, ziy@...dia.com, baolin.wang@...ux.alibaba.com,
        Liam.Howlett@...cle.com, ryan.roberts@....com, dev.jain@....com,
        corbet@....net, rostedt@...dmis.org, mhiramat@...nel.org,
        mathieu.desnoyers@...icios.com, akpm@...ux-foundation.org,
        baohua@...nel.org, willy@...radead.org, peterx@...hat.com,
        wangkefeng.wang@...wei.com, usamaarif642@...il.com,
        sunnanyong@...wei.com, vishal.moola@...il.com,
        thomas.hellstrom@...ux.intel.com, yang@...amperecomputing.com,
        kirill.shutemov@...ux.intel.com, aarcange@...hat.com,
        raquini@...hat.com, anshuman.khandual@....com, catalin.marinas@....com,
        tiwai@...e.de, will@...nel.org, dave.hansen@...ux.intel.com,
        jack@...e.cz, cl@...two.org, jglisse@...gle.com, surenb@...gle.com,
        zokeefe@...gle.com, hannes@...xchg.org, rientjes@...gle.com,
        mhocko@...e.com, rdunlap@...radead.org, hughd@...gle.com
Subject: Re: [PATCH v10 04/13] khugepaged: generalize alloc_charge_folio()

On Tue, Aug 19, 2025 at 07:41:56AM -0600, Nico Pache wrote:
> From: Dev Jain <dev.jain@....com>
>
> Pass order to alloc_charge_folio() and update mTHP statistics.
>
> Reviewed-by: Baolin Wang <baolin.wang@...ux.alibaba.com>
> Acked-by: David Hildenbrand <david@...hat.com>
> Co-developed-by: Nico Pache <npache@...hat.com>
> Signed-off-by: Nico Pache <npache@...hat.com>
> Signed-off-by: Dev Jain <dev.jain@....com>

LGTM so:

Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@...cle.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 a16a04841b96..7ccb93e22852 100644
> --- a/Documentation/admin-guide/mm/transhuge.rst
> +++ b/Documentation/admin-guide/mm/transhuge.rst
> @@ -630,6 +630,14 @@ 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 1ac0d06fb3c1..4ada5d1f7297 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 aac5f0a2cb54..20d005c2c61f 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -621,6 +621,8 @@ 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);
> @@ -686,6 +688,8 @@ 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 2d192ec961d2..77e0d8ee59a0 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -1079,21 +1079,26 @@ 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;
> @@ -1130,7 +1135,7 @@ 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;
>
> @@ -1863,7 +1868,7 @@ 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;
>
> --
> 2.50.1
>