linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
To: Nico Pache <npache@redhat.com>
Cc: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org,
	linux-mm@kvack.org, linux-doc@vger.kernel.org, david@redhat.com,
	ziy@nvidia.com, baolin.wang@linux.alibaba.com,
	Liam.Howlett@oracle.com, ryan.roberts@arm.com, dev.jain@arm.com,
	corbet@lwn.net, rostedt@goodmis.org, mhiramat@kernel.org,
	mathieu.desnoyers@efficios.com, akpm@linux-foundation.org,
	baohua@kernel.org, willy@infradead.org, peterx@redhat.com,
	wangkefeng.wang@huawei.com, usamaarif642@gmail.com,
	sunnanyong@huawei.com, vishal.moola@gmail.com,
	thomas.hellstrom@linux.intel.com, yang@os.amperecomputing.com,
	kas@kernel.org, aarcange@redhat.com, raquini@redhat.com,
	anshuman.khandual@arm.com, catalin.marinas@arm.com,
	tiwai@suse.de, will@kernel.org, dave.hansen@linux.intel.com,
	jack@suse.cz, cl@gentwo.org, jglisse@google.com,
	surenb@google.com, zokeefe@google.com, hannes@cmpxchg.org,
	rientjes@google.com, mhocko@suse.com, rdunlap@infradead.org,
	hughd@google.com, richard.weiyang@gmail.com,
	lance.yang@linux.dev, vbabka@suse.cz, rppt@kernel.org,
	jannh@google.com, pfalcato@suse.de
Subject: Re: [PATCH v12 mm-new 02/15] introduce collapse_single_pmd to unify khugepaged and madvise_collapse
Date: Mon, 27 Oct 2025 15:44:52 +0000	[thread overview]
Message-ID: <0b1d81bb-1d7c-41ab-8cd4-bbd8fa8d3785@lucifer.local> (raw)
In-Reply-To: <20251022183717.70829-3-npache@redhat.com>

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 properly indicates that this process is no longer valid to operate on.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@linux.alibaba.com>
> Acked-by: David Hildenbrand <david@redhat.com>
> Signed-off-by: Nico Pache <npache@redhat.com>

Thanks, this LGTM so:

Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.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
>


  parent reply	other threads:[~2025-10-27 15:45 UTC|newest]

Thread overview: 91+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-10-22 18:37 [PATCH v12 mm-new 00/15] khugepaged: mTHP support Nico Pache
2025-10-22 18:37 ` [PATCH v12 mm-new 01/15] khugepaged: rename hpage_collapse_* to collapse_* Nico Pache
2025-11-08  1:42   ` Wei Yang
2025-10-22 18:37 ` [PATCH v12 mm-new 02/15] introduce collapse_single_pmd to unify khugepaged and madvise_collapse Nico Pache
2025-10-27  9:00   ` Lance Yang
2025-10-27 15:44   ` Lorenzo Stoakes [this message]
2025-11-08  1:44   ` Wei Yang
2025-10-22 18:37 ` [PATCH v12 mm-new 03/15] khugepaged: generalize hugepage_vma_revalidate for mTHP support Nico Pache
2025-10-27  9:02   ` Lance Yang
2025-11-08  1:54   ` Wei Yang
2025-10-22 18:37 ` [PATCH v12 mm-new 04/15] khugepaged: generalize alloc_charge_folio() Nico Pache
2025-10-27  9:05   ` Lance Yang
2025-11-08  2:34   ` Wei Yang
2025-10-22 18:37 ` [PATCH v12 mm-new 05/15] khugepaged: generalize __collapse_huge_page_* for mTHP support Nico Pache
2025-10-27  9:17   ` Lance Yang
2025-10-27 16:00   ` Lorenzo Stoakes
2025-11-10 13:20     ` Nico Pache
2025-11-08  3:01   ` Wei Yang
2025-10-22 18:37 ` [PATCH v12 mm-new 06/15] khugepaged: introduce collapse_max_ptes_none helper function Nico Pache
2025-10-27 17:53   ` Lorenzo Stoakes
2025-10-28 10:09     ` Baolin Wang
2025-10-28 13:57       ` Nico Pache
2025-10-28 17:07       ` Lorenzo Stoakes
2025-10-28 17:56         ` David Hildenbrand
2025-10-28 18:09           ` Lorenzo Stoakes
2025-10-28 18:17             ` David Hildenbrand
2025-10-28 18:41               ` Lorenzo Stoakes
2025-10-29 15:04                 ` David Hildenbrand
2025-10-29 18:41                   ` Lorenzo Stoakes
2025-10-29 21:10                     ` Nico Pache
2025-10-30 18:03                       ` Lorenzo Stoakes
2025-10-29 20:45                   ` Nico Pache
2025-10-28 13:36     ` Nico Pache
2025-10-28 14:15       ` David Hildenbrand
2025-10-28 17:29         ` Lorenzo Stoakes
2025-10-28 17:36           ` Lorenzo Stoakes
2025-10-28 18:08           ` David Hildenbrand
2025-10-28 18:59             ` Lorenzo Stoakes
2025-10-28 19:08               ` Lorenzo Stoakes
2025-10-29  2:09               ` Baolin Wang
2025-10-29  2:49                 ` Nico Pache
2025-10-29 18:55                 ` Lorenzo Stoakes
2025-10-29 21:14                   ` Nico Pache
2025-10-30  1:15                     ` Baolin Wang
2025-10-29  2:47               ` Nico Pache
2025-10-29 18:58                 ` Lorenzo Stoakes
2025-10-29 21:23                   ` Nico Pache
2025-10-30 10:15                     ` Lorenzo Stoakes
2025-10-31 11:12               ` David Hildenbrand
2025-10-28 16:57       ` Lorenzo Stoakes
2025-10-28 17:49         ` David Hildenbrand
2025-10-28 17:59           ` Lorenzo Stoakes
2025-10-22 18:37 ` [PATCH v12 mm-new 07/15] khugepaged: generalize collapse_huge_page for mTHP collapse Nico Pache
2025-10-27  3:25   ` Baolin Wang
2025-11-06 18:14   ` Lorenzo Stoakes
2025-11-07  3:09     ` Dev Jain
2025-11-07  9:18       ` Lorenzo Stoakes
2025-11-07 19:33     ` Nico Pache
2025-10-22 18:37 ` [PATCH v12 mm-new 08/15] khugepaged: skip collapsing mTHP to smaller orders Nico Pache
2025-10-22 18:37 ` [PATCH v12 mm-new 09/15] khugepaged: add per-order mTHP collapse failure statistics Nico Pache
2025-11-06 18:45   ` Lorenzo Stoakes
2025-11-07 17:14     ` Nico Pache
2025-10-22 18:37 ` [PATCH v12 mm-new 10/15] khugepaged: improve tracepoints for mTHP orders Nico Pache
2025-10-22 18:37 ` [PATCH v12 mm-new 11/15] khugepaged: introduce collapse_allowable_orders helper function Nico Pache
2025-11-06 18:49   ` Lorenzo Stoakes
2025-11-07 18:01     ` Nico Pache
2025-10-22 18:37 ` [PATCH v12 mm-new 12/15] khugepaged: Introduce mTHP collapse support Nico Pache
2025-10-27  6:28   ` Baolin Wang
2025-11-09  2:08   ` Wei Yang
2025-11-11 21:56     ` Nico Pache
2025-11-19 11:53   ` Lorenzo Stoakes
2025-11-19 12:08     ` Lorenzo Stoakes
2025-11-20 22:32     ` Nico Pache
2025-10-22 18:37 ` [PATCH v12 mm-new 13/15] khugepaged: avoid unnecessary mTHP collapse attempts Nico Pache
2025-11-09  2:40   ` Wei Yang
2025-11-17 18:16     ` Nico Pache
2025-11-18  2:00       ` Wei Yang
2025-11-19 12:05   ` Lorenzo Stoakes
2025-11-26 23:16     ` Nico Pache
2025-11-26 23:29     ` Nico Pache
2025-10-22 18:37 ` [PATCH v12 mm-new 14/15] khugepaged: run khugepaged for all orders Nico Pache
2025-11-19 12:13   ` Lorenzo Stoakes
2025-11-20  6:37     ` Baolin Wang
2025-10-22 18:37 ` [PATCH v12 mm-new 15/15] Documentation: mm: update the admin guide for mTHP collapse Nico Pache
2025-10-22 19:52   ` Christoph Lameter (Ampere)
2025-10-22 20:22     ` David Hildenbrand
2025-10-23  8:00       ` Lorenzo Stoakes
2025-10-23  8:44         ` Pedro Falcato
2025-10-24 13:54           ` Zach O'Keefe
2025-10-23 23:41       ` Christoph Lameter (Ampere)
2025-10-22 20:13 ` [PATCH v12 mm-new 00/15] khugepaged: mTHP support Andrew Morton

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=0b1d81bb-1d7c-41ab-8cd4-bbd8fa8d3785@lucifer.local \
    --to=lorenzo.stoakes@oracle.com \
    --cc=Liam.Howlett@oracle.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=anshuman.khandual@arm.com \
    --cc=baohua@kernel.org \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=catalin.marinas@arm.com \
    --cc=cl@gentwo.org \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@linux.intel.com \
    --cc=david@redhat.com \
    --cc=dev.jain@arm.com \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=jack@suse.cz \
    --cc=jannh@google.com \
    --cc=jglisse@google.com \
    --cc=kas@kernel.org \
    --cc=lance.yang@linux.dev \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-trace-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mhiramat@kernel.org \
    --cc=mhocko@suse.com \
    --cc=npache@redhat.com \
    --cc=peterx@redhat.com \
    --cc=pfalcato@suse.de \
    --cc=raquini@redhat.com \
    --cc=rdunlap@infradead.org \
    --cc=richard.weiyang@gmail.com \
    --cc=rientjes@google.com \
    --cc=rostedt@goodmis.org \
    --cc=rppt@kernel.org \
    --cc=ryan.roberts@arm.com \
    --cc=sunnanyong@huawei.com \
    --cc=surenb@google.com \
    --cc=thomas.hellstrom@linux.intel.com \
    --cc=tiwai@suse.de \
    --cc=usamaarif642@gmail.com \
    --cc=vbabka@suse.cz \
    --cc=vishal.moola@gmail.com \
    --cc=wangkefeng.wang@huawei.com \
    --cc=will@kernel.org \
    --cc=willy@infradead.org \
    --cc=yang@os.amperecomputing.com \
    --cc=ziy@nvidia.com \
    --cc=zokeefe@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox