linux-kernel - Re: [PATCH mm-new v4 3/6] mm: khugepaged: just skip when the memory has been collapsed

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: <9924fc6c-e3ad-422a-ad60-756efccba0aa@kernel.org>
Date: Wed, 14 Jan 2026 12:40:50 +0100
From: "David Hildenbrand (Red Hat)" <david@...nel.org>
To: Vernon Yang <vernon2gm@...il.com>, akpm@...ux-foundation.org
Cc: lorenzo.stoakes@...cle.com, ziy@...dia.com, dev.jain@....com,
 baohua@...nel.org, lance.yang@...ux.dev, linux-mm@...ck.org,
 linux-kernel@...r.kernel.org, Vernon Yang <yanglincheng@...inos.cn>
Subject: Re: [PATCH mm-new v4 3/6] mm: khugepaged: just skip when the memory
 has been collapsed

On 1/11/26 13:19, Vernon Yang wrote:
> The following data is traced by bpftrace on a desktop system. After
> the system has been left idle for 10 minutes upon booting, a lot of
> SCAN_PMD_MAPPED or SCAN_NO_PTE_TABLE are observed during a full scan
> by khugepaged.
> 
> @scan_pmd_status[1]: 1           ## SCAN_SUCCEED
> @scan_pmd_status[6]: 2           ## SCAN_EXCEED_SHARED_PTE
> @scan_pmd_status[3]: 142         ## SCAN_PMD_MAPPED
> @scan_pmd_status[2]: 178         ## SCAN_NO_PTE_TABLE
> total progress size: 674 MB
> Total time         : 419 seconds ## include khugepaged_scan_sleep_millisecs
> 
> The khugepaged_scan list save all task that support collapse into hugepage,
> as long as the task is not destroyed, khugepaged will not remove it from
> the khugepaged_scan list. This exist a phenomenon where task has already
> collapsed all memory regions into hugepage, but khugepaged continues to
> scan it, which wastes CPU time and invalid, and due to
> khugepaged_scan_sleep_millisecs (default 10s) causes a long wait for
> scanning a large number of invalid task, so scanning really valid task
> is later.
> 
> After applying this patch, when the memory is either SCAN_PMD_MAPPED or
> SCAN_NO_PTE_TABLE, just skip it, as follow:
> 
> @scan_pmd_status[6]: 2
> @scan_pmd_status[3]: 147
> @scan_pmd_status[2]: 173
> total progress size: 45 MB
> Total time         : 20 seconds
> 
> Signed-off-by: Vernon Yang <yanglincheng@...inos.cn>
> ---
>   mm/khugepaged.c | 17 +++++++++++------
>   1 file changed, 11 insertions(+), 6 deletions(-)
> 
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index 5c6015ac7b5e..6df2857d94c6 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -68,7 +68,10 @@ enum scan_result {
>   static struct task_struct *khugepaged_thread __read_mostly;
>   static DEFINE_MUTEX(khugepaged_mutex);
>   
> -/* default scan 8*HPAGE_PMD_NR ptes (or vmas) every 10 second */
> +/*
> + * default scan 8*HPAGE_PMD_NR ptes, pmd_mapped, no_pte_table or vmas
> + * every 10 second.
> + */
>   static unsigned int khugepaged_pages_to_scan __read_mostly;
>   static unsigned int khugepaged_pages_collapsed;
>   static unsigned int khugepaged_full_scans;
> @@ -1267,7 +1270,7 @@ static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm,
>   	result = find_pmd_or_thp_or_none(mm, start_addr, &pmd);
>   	if (result != SCAN_SUCCEED) {
>   		if (cur_progress)
> -			*cur_progress = HPAGE_PMD_NR;
> +			*cur_progress = 1;
>   		goto out;
>   	}
>   
> @@ -1276,7 +1279,7 @@ static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm,
>   	pte = pte_offset_map_lock(mm, pmd, start_addr, &ptl);
>   	if (!pte) {
>   		if (cur_progress)
> -			*cur_progress = HPAGE_PMD_NR;
> +			*cur_progress = 1;
>   		result = SCAN_NO_PTE_TABLE;
>   		goto out;
>   	}

The above checks are clear.

> @@ -2347,9 +2350,6 @@ static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, unsigned
>   			continue;
>   		}
>   
> -		if (cur_progress)
> -			*cur_progress += folio_nr_pages(folio);
> -

This is a all a bit hairy.

Assume we found a single 4k folio in the xarray, but then collapse a 2M THP.

Is the progress really "1" ?

What about shmem swap entries (xa_is_value)?

So I think the whole file path needs more thought

-- 
Cheers

David