| 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
| ||
|
Message-ID: <0b1d81bb-1d7c-41ab-8cd4-bbd8fa8d3785@lucifer.local>
Date: Mon, 27 Oct 2025 15:44:52 +0000
From: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
To: Nico Pache <npache@...hat.com>
Cc: linux-kernel@...r.kernel.org, linux-trace-kernel@...r.kernel.org,
linux-mm@...ck.org, linux-doc@...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,
kas@...nel.org, 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,
richard.weiyang@...il.com, lance.yang@...ux.dev, vbabka@...e.cz,
rppt@...nel.org, jannh@...gle.com, pfalcato@...e.de
Subject: Re: [PATCH v12 mm-new 02/15] introduce collapse_single_pmd to unify
khugepaged and madvise_collapse
On Wed, Oct 22, 2025 at 12:37:04PM -0600, Nico Pache wrote:
> The khugepaged daemon and madvise_collapse have two different
> implementations that do almost the same thing.
>
> Create collapse_single_pmd to increase code reuse and create an entry
> point to these two users.
>
> Refactor madvise_collapse and collapse_scan_mm_slot to use the new
> collapse_single_pmd function. This introduces a minor behavioral change
> that is most likely an undiscovered bug. The current implementation of
> khugepaged tests collapse_test_exit_or_disable before calling
> collapse_pte_mapped_thp, but we weren't doing it in the madvise_collapse
> case. By unifying these two callers madvise_collapse now also performs
> this check. We also modify the return value to be SCAN_ANY_PROCESS which
> properly indicates that this process is no longer valid to operate on.
>
> We also guard the khugepaged_pages_collapsed variable to ensure its only
> incremented for khugepaged.
>
> Reviewed-by: Baolin Wang <baolin.wang@...ux.alibaba.com>
> Acked-by: David Hildenbrand <david@...hat.com>
> Signed-off-by: Nico Pache <npache@...hat.com>
Thanks, this LGTM so:
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
> ---
> mm/khugepaged.c | 97 ++++++++++++++++++++++++++-----------------------
> 1 file changed, 52 insertions(+), 45 deletions(-)
>
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index 6c4abc7f45cf..36e31d99e507 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -2370,6 +2370,53 @@ static int collapse_scan_file(struct mm_struct *mm, unsigned long addr,
> return result;
> }
>
> +/*
> + * Try to collapse a single PMD starting at a PMD aligned addr, and return
> + * the results.
> + */
> +static int collapse_single_pmd(unsigned long addr,
> + struct vm_area_struct *vma, bool *mmap_locked,
> + struct collapse_control *cc)
> +{
> + struct mm_struct *mm = vma->vm_mm;
> + int result;
> + struct file *file;
> + pgoff_t pgoff;
> +
> + if (vma_is_anonymous(vma)) {
> + result = collapse_scan_pmd(mm, vma, addr, mmap_locked, cc);
> + goto end;
> + }
> +
> + file = get_file(vma->vm_file);
> + pgoff = linear_page_index(vma, addr);
> +
> + mmap_read_unlock(mm);
> + *mmap_locked = false;
> + result = collapse_scan_file(mm, addr, file, pgoff, cc);
> + fput(file);
> + if (result != SCAN_PTE_MAPPED_HUGEPAGE)
> + goto end;
> +
> + mmap_read_lock(mm);
> + *mmap_locked = true;
> + if (collapse_test_exit_or_disable(mm)) {
> + mmap_read_unlock(mm);
> + *mmap_locked = false;
> + return SCAN_ANY_PROCESS;
> + }
> + result = collapse_pte_mapped_thp(mm, addr, !cc->is_khugepaged);
> + if (result == SCAN_PMD_MAPPED)
> + result = SCAN_SUCCEED;
> + mmap_read_unlock(mm);
> + *mmap_locked = false;
> +
> +end:
> + if (cc->is_khugepaged && result == SCAN_SUCCEED)
> + ++khugepaged_pages_collapsed;
> + return result;
> +}
> +
> static unsigned int collapse_scan_mm_slot(unsigned int pages, int *result,
> struct collapse_control *cc)
> __releases(&khugepaged_mm_lock)
> @@ -2440,34 +2487,9 @@ static unsigned int collapse_scan_mm_slot(unsigned int pages, int *result,
> VM_BUG_ON(khugepaged_scan.address < hstart ||
> khugepaged_scan.address + HPAGE_PMD_SIZE >
> hend);
> - if (!vma_is_anonymous(vma)) {
> - struct file *file = get_file(vma->vm_file);
> - pgoff_t pgoff = linear_page_index(vma,
> - khugepaged_scan.address);
> -
> - mmap_read_unlock(mm);
> - mmap_locked = false;
> - *result = collapse_scan_file(mm,
> - khugepaged_scan.address, file, pgoff, cc);
> - fput(file);
> - if (*result == SCAN_PTE_MAPPED_HUGEPAGE) {
> - mmap_read_lock(mm);
> - if (collapse_test_exit_or_disable(mm))
> - goto breakouterloop;
> - *result = collapse_pte_mapped_thp(mm,
> - khugepaged_scan.address, false);
> - if (*result == SCAN_PMD_MAPPED)
> - *result = SCAN_SUCCEED;
> - mmap_read_unlock(mm);
> - }
> - } else {
> - *result = collapse_scan_pmd(mm, vma,
> - khugepaged_scan.address, &mmap_locked, cc);
> - }
> -
> - if (*result == SCAN_SUCCEED)
> - ++khugepaged_pages_collapsed;
>
> + *result = collapse_single_pmd(khugepaged_scan.address,
> + vma, &mmap_locked, cc);
> /* move to next address */
> khugepaged_scan.address += HPAGE_PMD_SIZE;
> progress += HPAGE_PMD_NR;
> @@ -2781,34 +2803,19 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
> mmap_assert_locked(mm);
> memset(cc->node_load, 0, sizeof(cc->node_load));
> nodes_clear(cc->alloc_nmask);
> - if (!vma_is_anonymous(vma)) {
> - struct file *file = get_file(vma->vm_file);
> - pgoff_t pgoff = linear_page_index(vma, addr);
>
> - mmap_read_unlock(mm);
> - mmap_locked = false;
> - result = collapse_scan_file(mm, addr, file, pgoff, cc);
> - fput(file);
> - } else {
> - result = collapse_scan_pmd(mm, vma, addr,
> - &mmap_locked, cc);
> - }
> + result = collapse_single_pmd(addr, vma, &mmap_locked, cc);
> +
> if (!mmap_locked)
> *lock_dropped = true;
>
> -handle_result:
> switch (result) {
> case SCAN_SUCCEED:
> case SCAN_PMD_MAPPED:
> ++thps;
> break;
> - case SCAN_PTE_MAPPED_HUGEPAGE:
> - BUG_ON(mmap_locked);
> - mmap_read_lock(mm);
> - result = collapse_pte_mapped_thp(mm, addr, true);
> - mmap_read_unlock(mm);
> - goto handle_result;
> /* Whitelisted set of results where continuing OK */
> + case SCAN_PTE_MAPPED_HUGEPAGE:
> case SCAN_PMD_NULL:
> case SCAN_PTE_NON_PRESENT:
> case SCAN_PTE_UFFD_WP:
> --
> 2.51.0
>
Powered by blists - more mailing lists