diff mbox series

[v2,2/5] mm: damon must atomically clear young on ptes and pmds

Message ID 20230518110727.2106156-3-ryan.roberts@arm.com (mailing list archive)
State New
Headers show
Series Encapsulate PTE contents from non-arch code | expand

Commit Message

Ryan Roberts May 18, 2023, 11:07 a.m. UTC
It is racy to non-atomically read a pte, then clear the young bit, then
write it back as this could discard dirty information. Further, it is
bad practice to directly set a pte entry within a table. Instead
clearing young must go through the arch-provided helper,
ptep_test_and_clear_young() to ensure it is modified atomically and to
give the arch code visibility and allow it to check (and potentially
modify) the operation.

Fixes: 46c3a0accdc4 ("mm/damon/vaddr: separate commonly usable functions")
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
---
 mm/damon/ops-common.c | 16 ++++++----------
 mm/damon/ops-common.h |  4 ++--
 mm/damon/paddr.c      |  4 ++--
 mm/damon/vaddr.c      |  4 ++--
 4 files changed, 12 insertions(+), 16 deletions(-)

Comments

SeongJae Park May 18, 2023, 5:13 p.m. UTC | #1
Hi Ryan,


Nit.  For consistency of DAMON commits subjects, I'd prefer something like
"mm/damon/ops-common: atomically test and clear young on ptes and pmds".

On Thu, 18 May 2023 12:07:24 +0100 Ryan Roberts <ryan.roberts@arm.com> wrote:

> It is racy to non-atomically read a pte, then clear the young bit, then
> write it back as this could discard dirty information. Further, it is
> bad practice to directly set a pte entry within a table. Instead
> clearing young must go through the arch-provided helper,
> ptep_test_and_clear_young() to ensure it is modified atomically and to
> give the arch code visibility and allow it to check (and potentially
> modify) the operation.
> 
> Fixes: 46c3a0accdc4 ("mm/damon/vaddr: separate commonly usable functions")

Nit.  The commit is only for refactoring.  The original code camde from commit
3f49584b262c ("mm/damon: implement primitives for the virtual memory address
spaces").

> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> Reviewed-by: Zi Yan <ziy@nvidia.com>

Other than above nits,

Reviewed-by: SeongJae Park <sj@kernel.org>


Thanks,
SJ

> ---
>  mm/damon/ops-common.c | 16 ++++++----------
>  mm/damon/ops-common.h |  4 ++--
>  mm/damon/paddr.c      |  4 ++--
>  mm/damon/vaddr.c      |  4 ++--
>  4 files changed, 12 insertions(+), 16 deletions(-)
> 
> diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c
> index cc63cf953636..acc264b97903 100644
> --- a/mm/damon/ops-common.c
> +++ b/mm/damon/ops-common.c
> @@ -37,7 +37,7 @@ struct folio *damon_get_folio(unsigned long pfn)
>  	return folio;
>  }
>  
> -void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
> +void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr)
>  {
>  	bool referenced = false;
>  	struct folio *folio = damon_get_folio(pte_pfn(*pte));
> @@ -45,13 +45,11 @@ void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
>  	if (!folio)
>  		return;
>  
> -	if (pte_young(*pte)) {
> +	if (ptep_test_and_clear_young(vma, addr, pte))
>  		referenced = true;
> -		*pte = pte_mkold(*pte);
> -	}
>  
>  #ifdef CONFIG_MMU_NOTIFIER
> -	if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE))
> +	if (mmu_notifier_clear_young(vma->vm_mm, addr, addr + PAGE_SIZE))
>  		referenced = true;
>  #endif /* CONFIG_MMU_NOTIFIER */
>  
> @@ -62,7 +60,7 @@ void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
>  	folio_put(folio);
>  }
>  
> -void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr)
> +void damon_pmdp_mkold(pmd_t *pmd, struct vm_area_struct *vma, unsigned long addr)
>  {
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>  	bool referenced = false;
> @@ -71,13 +69,11 @@ void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr)
>  	if (!folio)
>  		return;
>  
> -	if (pmd_young(*pmd)) {
> +	if (pmdp_test_and_clear_young(vma, addr, pmd))
>  		referenced = true;
> -		*pmd = pmd_mkold(*pmd);
> -	}
>  
>  #ifdef CONFIG_MMU_NOTIFIER
> -	if (mmu_notifier_clear_young(mm, addr, addr + HPAGE_PMD_SIZE))
> +	if (mmu_notifier_clear_young(vma->vm_mm, addr, addr + HPAGE_PMD_SIZE))
>  		referenced = true;
>  #endif /* CONFIG_MMU_NOTIFIER */
>  
> diff --git a/mm/damon/ops-common.h b/mm/damon/ops-common.h
> index 14f4bc69f29b..18d837d11bce 100644
> --- a/mm/damon/ops-common.h
> +++ b/mm/damon/ops-common.h
> @@ -9,8 +9,8 @@
>  
>  struct folio *damon_get_folio(unsigned long pfn);
>  
> -void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr);
> -void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr);
> +void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr);
> +void damon_pmdp_mkold(pmd_t *pmd, struct vm_area_struct *vma, unsigned long addr);
>  
>  int damon_cold_score(struct damon_ctx *c, struct damon_region *r,
>  			struct damos *s);
> diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
> index 467b99166b43..5b3a3463d078 100644
> --- a/mm/damon/paddr.c
> +++ b/mm/damon/paddr.c
> @@ -24,9 +24,9 @@ static bool __damon_pa_mkold(struct folio *folio, struct vm_area_struct *vma,
>  	while (page_vma_mapped_walk(&pvmw)) {
>  		addr = pvmw.address;
>  		if (pvmw.pte)
> -			damon_ptep_mkold(pvmw.pte, vma->vm_mm, addr);
> +			damon_ptep_mkold(pvmw.pte, vma, addr);
>  		else
> -			damon_pmdp_mkold(pvmw.pmd, vma->vm_mm, addr);
> +			damon_pmdp_mkold(pvmw.pmd, vma, addr);
>  	}
>  	return true;
>  }
> diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
> index 1fec16d7263e..37994fb6120c 100644
> --- a/mm/damon/vaddr.c
> +++ b/mm/damon/vaddr.c
> @@ -311,7 +311,7 @@ static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
>  		}
>  
>  		if (pmd_trans_huge(*pmd)) {
> -			damon_pmdp_mkold(pmd, walk->mm, addr);
> +			damon_pmdp_mkold(pmd, walk->vma, addr);
>  			spin_unlock(ptl);
>  			return 0;
>  		}
> @@ -323,7 +323,7 @@ static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
>  	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
>  	if (!pte_present(*pte))
>  		goto out;
> -	damon_ptep_mkold(pte, walk->mm, addr);
> +	damon_ptep_mkold(pte, walk->vma, addr);
>  out:
>  	pte_unmap_unlock(pte, ptl);
>  	return 0;
> -- 
> 2.25.1
> 
>
Yu Zhao May 18, 2023, 11:19 p.m. UTC | #2
On Thu, May 18, 2023 at 5:07 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
>
> It is racy to non-atomically read a pte, then clear the young bit, then
> write it back as this could discard dirty information. Further, it is
> bad practice to directly set a pte entry within a table. Instead
> clearing young must go through the arch-provided helper,
> ptep_test_and_clear_young() to ensure it is modified atomically and to
> give the arch code visibility and allow it to check (and potentially
> modify) the operation.
>
> Fixes: 46c3a0accdc4 ("mm/damon/vaddr: separate commonly usable functions")

This should be a separate patch, since it's independent from what the
series tries to do.

And that patch should cc stable, since it fixes user data corruption.

> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> Reviewed-by: Zi Yan <ziy@nvidia.com>
> ---
>  mm/damon/ops-common.c | 16 ++++++----------
>  mm/damon/ops-common.h |  4 ++--
>  mm/damon/paddr.c      |  4 ++--
>  mm/damon/vaddr.c      |  4 ++--
>  4 files changed, 12 insertions(+), 16 deletions(-)
>
> diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c
> index cc63cf953636..acc264b97903 100644
> --- a/mm/damon/ops-common.c
> +++ b/mm/damon/ops-common.c
> @@ -37,7 +37,7 @@ struct folio *damon_get_folio(unsigned long pfn)
>         return folio;
>  }
>
> -void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
> +void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr)
>  {
>         bool referenced = false;
>         struct folio *folio = damon_get_folio(pte_pfn(*pte));
> @@ -45,13 +45,11 @@ void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
>         if (!folio)
>                 return;
>
> -       if (pte_young(*pte)) {
> +       if (ptep_test_and_clear_young(vma, addr, pte))
>                 referenced = true;
> -               *pte = pte_mkold(*pte);
> -       }
>
>  #ifdef CONFIG_MMU_NOTIFIER
> -       if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE))
> +       if (mmu_notifier_clear_young(vma->vm_mm, addr, addr + PAGE_SIZE))
>                 referenced = true;
>  #endif /* CONFIG_MMU_NOTIFIER */

Use ptep_clear_young_notify(). Similar below.
Ryan Roberts May 19, 2023, 8:53 a.m. UTC | #3
On 18/05/2023 18:13, SeongJae Park wrote:
> Hi Ryan,
> 
> 
> Nit.  For consistency of DAMON commits subjects, I'd prefer something like
> "mm/damon/ops-common: atomically test and clear young on ptes and pmds".
> 
> On Thu, 18 May 2023 12:07:24 +0100 Ryan Roberts <ryan.roberts@arm.com> wrote:
> 
>> It is racy to non-atomically read a pte, then clear the young bit, then
>> write it back as this could discard dirty information. Further, it is
>> bad practice to directly set a pte entry within a table. Instead
>> clearing young must go through the arch-provided helper,
>> ptep_test_and_clear_young() to ensure it is modified atomically and to
>> give the arch code visibility and allow it to check (and potentially
>> modify) the operation.
>>
>> Fixes: 46c3a0accdc4 ("mm/damon/vaddr: separate commonly usable functions")
> 
> Nit.  The commit is only for refactoring.  The original code camde from commit
> 3f49584b262c ("mm/damon: implement primitives for the virtual memory address
> spaces").
> 
>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>> Reviewed-by: Zi Yan <ziy@nvidia.com>
> 
> Other than above nits,
> 
> Reviewed-by: SeongJae Park <sj@kernel.org>

Thanks for the reviews! I'll fix the nits you raised for v3.

> 
> 
> Thanks,
> SJ
>
Ryan Roberts May 19, 2023, 9:02 a.m. UTC | #4
On 19/05/2023 00:19, Yu Zhao wrote:
> On Thu, May 18, 2023 at 5:07 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
>>
>> It is racy to non-atomically read a pte, then clear the young bit, then
>> write it back as this could discard dirty information. Further, it is
>> bad practice to directly set a pte entry within a table. Instead
>> clearing young must go through the arch-provided helper,
>> ptep_test_and_clear_young() to ensure it is modified atomically and to
>> give the arch code visibility and allow it to check (and potentially
>> modify) the operation.
>>
>> Fixes: 46c3a0accdc4 ("mm/damon/vaddr: separate commonly usable functions")
> 
> This should be a separate patch, since it's independent from what the
> series tries to do.
> 
> And that patch should cc stable, since it fixes user data corruption.

Fair point. The first 3 patches are fixes for issues I found during the
conversion. So if you're ok with it, I'll split into 2 series; the first 3
patches in the first, and the conversion to ptep_deref() (or ptep_get(), as per
your comments in the other thread) in the second. I guess the whole first series
should go to stable.

Let me know if you disagree.

> 
>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>> Reviewed-by: Zi Yan <ziy@nvidia.com>
>> ---
>>  mm/damon/ops-common.c | 16 ++++++----------
>>  mm/damon/ops-common.h |  4 ++--
>>  mm/damon/paddr.c      |  4 ++--
>>  mm/damon/vaddr.c      |  4 ++--
>>  4 files changed, 12 insertions(+), 16 deletions(-)
>>
>> diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c
>> index cc63cf953636..acc264b97903 100644
>> --- a/mm/damon/ops-common.c
>> +++ b/mm/damon/ops-common.c
>> @@ -37,7 +37,7 @@ struct folio *damon_get_folio(unsigned long pfn)
>>         return folio;
>>  }
>>
>> -void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
>> +void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr)
>>  {
>>         bool referenced = false;
>>         struct folio *folio = damon_get_folio(pte_pfn(*pte));
>> @@ -45,13 +45,11 @@ void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
>>         if (!folio)
>>                 return;
>>
>> -       if (pte_young(*pte)) {
>> +       if (ptep_test_and_clear_young(vma, addr, pte))
>>                 referenced = true;
>> -               *pte = pte_mkold(*pte);
>> -       }
>>
>>  #ifdef CONFIG_MMU_NOTIFIER
>> -       if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE))
>> +       if (mmu_notifier_clear_young(vma->vm_mm, addr, addr + PAGE_SIZE))
>>                 referenced = true;
>>  #endif /* CONFIG_MMU_NOTIFIER */
> 
> Use ptep_clear_young_notify(). Similar below.

This looks sensible but I'd like clarification from SeongJae: Are you happy for
me to do this refactoring as part of the patch?

Thanks,
Ryan
SeongJae Park May 19, 2023, 7:54 p.m. UTC | #5
On Fri, 19 May 2023 10:02:48 +0100 Ryan Roberts <ryan.roberts@arm.com> wrote:

> On 19/05/2023 00:19, Yu Zhao wrote:
> > On Thu, May 18, 2023 at 5:07 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
> >>
> >> It is racy to non-atomically read a pte, then clear the young bit, then
> >> write it back as this could discard dirty information. Further, it is
> >> bad practice to directly set a pte entry within a table. Instead
> >> clearing young must go through the arch-provided helper,
> >> ptep_test_and_clear_young() to ensure it is modified atomically and to
> >> give the arch code visibility and allow it to check (and potentially
> >> modify) the operation.
> >>
> >> Fixes: 46c3a0accdc4 ("mm/damon/vaddr: separate commonly usable functions")
> > 
> > This should be a separate patch, since it's independent from what the
> > series tries to do.
> > 
> > And that patch should cc stable, since it fixes user data corruption.
> 
> Fair point. The first 3 patches are fixes for issues I found during the
> conversion. So if you're ok with it, I'll split into 2 series; the first 3
> patches in the first, and the conversion to ptep_deref() (or ptep_get(), as per
> your comments in the other thread) in the second. I guess the whole first series
> should go to stable.
> 
> Let me know if you disagree.
> 
> > 
> >> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> >> Reviewed-by: Zi Yan <ziy@nvidia.com>
> >> ---
> >>  mm/damon/ops-common.c | 16 ++++++----------
> >>  mm/damon/ops-common.h |  4 ++--
> >>  mm/damon/paddr.c      |  4 ++--
> >>  mm/damon/vaddr.c      |  4 ++--
> >>  4 files changed, 12 insertions(+), 16 deletions(-)
> >>
> >> diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c
> >> index cc63cf953636..acc264b97903 100644
> >> --- a/mm/damon/ops-common.c
> >> +++ b/mm/damon/ops-common.c
> >> @@ -37,7 +37,7 @@ struct folio *damon_get_folio(unsigned long pfn)
> >>         return folio;
> >>  }
> >>
> >> -void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
> >> +void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr)
> >>  {
> >>         bool referenced = false;
> >>         struct folio *folio = damon_get_folio(pte_pfn(*pte));
> >> @@ -45,13 +45,11 @@ void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
> >>         if (!folio)
> >>                 return;
> >>
> >> -       if (pte_young(*pte)) {
> >> +       if (ptep_test_and_clear_young(vma, addr, pte))
> >>                 referenced = true;
> >> -               *pte = pte_mkold(*pte);
> >> -       }
> >>
> >>  #ifdef CONFIG_MMU_NOTIFIER
> >> -       if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE))
> >> +       if (mmu_notifier_clear_young(vma->vm_mm, addr, addr + PAGE_SIZE))
> >>                 referenced = true;
> >>  #endif /* CONFIG_MMU_NOTIFIER */
> > 
> > Use ptep_clear_young_notify(). Similar below.
> 
> This looks sensible but I'd like clarification from SeongJae: Are you happy for
> me to do this refactoring as part of the patch?

Yes, I would be happy for that :)  Nevertheless, because that's a refactoring
rather than a fix, I'd be happier if you could do that with a separate patch.


Thanks,
SJ

> 
> Thanks,
> Ryan
>
Ryan Roberts May 22, 2023, 8:53 a.m. UTC | #6
On 19/05/2023 20:54, SeongJae Park wrote:
> On Fri, 19 May 2023 10:02:48 +0100 Ryan Roberts <ryan.roberts@arm.com> wrote:
> 
>> On 19/05/2023 00:19, Yu Zhao wrote:
>>> On Thu, May 18, 2023 at 5:07 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
>>>>
>>>> It is racy to non-atomically read a pte, then clear the young bit, then
>>>> write it back as this could discard dirty information. Further, it is
>>>> bad practice to directly set a pte entry within a table. Instead
>>>> clearing young must go through the arch-provided helper,
>>>> ptep_test_and_clear_young() to ensure it is modified atomically and to
>>>> give the arch code visibility and allow it to check (and potentially
>>>> modify) the operation.
>>>>
>>>> Fixes: 46c3a0accdc4 ("mm/damon/vaddr: separate commonly usable functions")
>>>
>>> This should be a separate patch, since it's independent from what the
>>> series tries to do.
>>>
>>> And that patch should cc stable, since it fixes user data corruption.
>>
>> Fair point. The first 3 patches are fixes for issues I found during the
>> conversion. So if you're ok with it, I'll split into 2 series; the first 3
>> patches in the first, and the conversion to ptep_deref() (or ptep_get(), as per
>> your comments in the other thread) in the second. I guess the whole first series
>> should go to stable.
>>
>> Let me know if you disagree.
>>
>>>
>>>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>>>> Reviewed-by: Zi Yan <ziy@nvidia.com>
>>>> ---
>>>>  mm/damon/ops-common.c | 16 ++++++----------
>>>>  mm/damon/ops-common.h |  4 ++--
>>>>  mm/damon/paddr.c      |  4 ++--
>>>>  mm/damon/vaddr.c      |  4 ++--
>>>>  4 files changed, 12 insertions(+), 16 deletions(-)
>>>>
>>>> diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c
>>>> index cc63cf953636..acc264b97903 100644
>>>> --- a/mm/damon/ops-common.c
>>>> +++ b/mm/damon/ops-common.c
>>>> @@ -37,7 +37,7 @@ struct folio *damon_get_folio(unsigned long pfn)
>>>>         return folio;
>>>>  }
>>>>
>>>> -void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
>>>> +void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr)
>>>>  {
>>>>         bool referenced = false;
>>>>         struct folio *folio = damon_get_folio(pte_pfn(*pte));
>>>> @@ -45,13 +45,11 @@ void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
>>>>         if (!folio)
>>>>                 return;
>>>>
>>>> -       if (pte_young(*pte)) {
>>>> +       if (ptep_test_and_clear_young(vma, addr, pte))
>>>>                 referenced = true;
>>>> -               *pte = pte_mkold(*pte);
>>>> -       }
>>>>
>>>>  #ifdef CONFIG_MMU_NOTIFIER
>>>> -       if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE))
>>>> +       if (mmu_notifier_clear_young(vma->vm_mm, addr, addr + PAGE_SIZE))
>>>>                 referenced = true;
>>>>  #endif /* CONFIG_MMU_NOTIFIER */
>>>
>>> Use ptep_clear_young_notify(). Similar below.
>>
>> This looks sensible but I'd like clarification from SeongJae: Are you happy for
>> me to do this refactoring as part of the patch?
> 
> Yes, I would be happy for that :)  Nevertheless, because that's a refactoring
> rather than a fix, I'd be happier if you could do that with a separate patch.

Great - I'll do it like this for v3.

> 
> 
> Thanks,
> SJ
> 
>>
>> Thanks,
>> Ryan
>>
Mike Rapoport May 24, 2023, 6:49 p.m. UTC | #7
On Thu, May 18, 2023 at 12:07:24PM +0100, Ryan Roberts wrote:
> It is racy to non-atomically read a pte, then clear the young bit, then
> write it back as this could discard dirty information. Further, it is
> bad practice to directly set a pte entry within a table. Instead
> clearing young must go through the arch-provided helper,
> ptep_test_and_clear_young() to ensure it is modified atomically and to
> give the arch code visibility and allow it to check (and potentially
> modify) the operation.
> 
> Fixes: 46c3a0accdc4 ("mm/damon/vaddr: separate commonly usable functions")
> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> Reviewed-by: Zi Yan <ziy@nvidia.com>

Reviewed-by: Mike Rapoport (IBM) <rppt@kernel.org>

> ---
>  mm/damon/ops-common.c | 16 ++++++----------
>  mm/damon/ops-common.h |  4 ++--
>  mm/damon/paddr.c      |  4 ++--
>  mm/damon/vaddr.c      |  4 ++--
>  4 files changed, 12 insertions(+), 16 deletions(-)
> 
> diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c
> index cc63cf953636..acc264b97903 100644
> --- a/mm/damon/ops-common.c
> +++ b/mm/damon/ops-common.c
> @@ -37,7 +37,7 @@ struct folio *damon_get_folio(unsigned long pfn)
>  	return folio;
>  }
>  
> -void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
> +void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr)
>  {
>  	bool referenced = false;
>  	struct folio *folio = damon_get_folio(pte_pfn(*pte));
> @@ -45,13 +45,11 @@ void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
>  	if (!folio)
>  		return;
>  
> -	if (pte_young(*pte)) {
> +	if (ptep_test_and_clear_young(vma, addr, pte))
>  		referenced = true;
> -		*pte = pte_mkold(*pte);
> -	}
>  
>  #ifdef CONFIG_MMU_NOTIFIER
> -	if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE))
> +	if (mmu_notifier_clear_young(vma->vm_mm, addr, addr + PAGE_SIZE))
>  		referenced = true;
>  #endif /* CONFIG_MMU_NOTIFIER */
>  
> @@ -62,7 +60,7 @@ void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
>  	folio_put(folio);
>  }
>  
> -void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr)
> +void damon_pmdp_mkold(pmd_t *pmd, struct vm_area_struct *vma, unsigned long addr)
>  {
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>  	bool referenced = false;
> @@ -71,13 +69,11 @@ void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr)
>  	if (!folio)
>  		return;
>  
> -	if (pmd_young(*pmd)) {
> +	if (pmdp_test_and_clear_young(vma, addr, pmd))
>  		referenced = true;
> -		*pmd = pmd_mkold(*pmd);
> -	}
>  
>  #ifdef CONFIG_MMU_NOTIFIER
> -	if (mmu_notifier_clear_young(mm, addr, addr + HPAGE_PMD_SIZE))
> +	if (mmu_notifier_clear_young(vma->vm_mm, addr, addr + HPAGE_PMD_SIZE))
>  		referenced = true;
>  #endif /* CONFIG_MMU_NOTIFIER */
>  
> diff --git a/mm/damon/ops-common.h b/mm/damon/ops-common.h
> index 14f4bc69f29b..18d837d11bce 100644
> --- a/mm/damon/ops-common.h
> +++ b/mm/damon/ops-common.h
> @@ -9,8 +9,8 @@
>  
>  struct folio *damon_get_folio(unsigned long pfn);
>  
> -void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr);
> -void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr);
> +void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr);
> +void damon_pmdp_mkold(pmd_t *pmd, struct vm_area_struct *vma, unsigned long addr);
>  
>  int damon_cold_score(struct damon_ctx *c, struct damon_region *r,
>  			struct damos *s);
> diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
> index 467b99166b43..5b3a3463d078 100644
> --- a/mm/damon/paddr.c
> +++ b/mm/damon/paddr.c
> @@ -24,9 +24,9 @@ static bool __damon_pa_mkold(struct folio *folio, struct vm_area_struct *vma,
>  	while (page_vma_mapped_walk(&pvmw)) {
>  		addr = pvmw.address;
>  		if (pvmw.pte)
> -			damon_ptep_mkold(pvmw.pte, vma->vm_mm, addr);
> +			damon_ptep_mkold(pvmw.pte, vma, addr);
>  		else
> -			damon_pmdp_mkold(pvmw.pmd, vma->vm_mm, addr);
> +			damon_pmdp_mkold(pvmw.pmd, vma, addr);
>  	}
>  	return true;
>  }
> diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
> index 1fec16d7263e..37994fb6120c 100644
> --- a/mm/damon/vaddr.c
> +++ b/mm/damon/vaddr.c
> @@ -311,7 +311,7 @@ static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
>  		}
>  
>  		if (pmd_trans_huge(*pmd)) {
> -			damon_pmdp_mkold(pmd, walk->mm, addr);
> +			damon_pmdp_mkold(pmd, walk->vma, addr);
>  			spin_unlock(ptl);
>  			return 0;
>  		}
> @@ -323,7 +323,7 @@ static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
>  	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
>  	if (!pte_present(*pte))
>  		goto out;
> -	damon_ptep_mkold(pte, walk->mm, addr);
> +	damon_ptep_mkold(pte, walk->vma, addr);
>  out:
>  	pte_unmap_unlock(pte, ptl);
>  	return 0;
> -- 
> 2.25.1
> 
>
diff mbox series

Patch

diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c
index cc63cf953636..acc264b97903 100644
--- a/mm/damon/ops-common.c
+++ b/mm/damon/ops-common.c
@@ -37,7 +37,7 @@  struct folio *damon_get_folio(unsigned long pfn)
 	return folio;
 }
 
-void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
+void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr)
 {
 	bool referenced = false;
 	struct folio *folio = damon_get_folio(pte_pfn(*pte));
@@ -45,13 +45,11 @@  void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
 	if (!folio)
 		return;
 
-	if (pte_young(*pte)) {
+	if (ptep_test_and_clear_young(vma, addr, pte))
 		referenced = true;
-		*pte = pte_mkold(*pte);
-	}
 
 #ifdef CONFIG_MMU_NOTIFIER
-	if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE))
+	if (mmu_notifier_clear_young(vma->vm_mm, addr, addr + PAGE_SIZE))
 		referenced = true;
 #endif /* CONFIG_MMU_NOTIFIER */
 
@@ -62,7 +60,7 @@  void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
 	folio_put(folio);
 }
 
-void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr)
+void damon_pmdp_mkold(pmd_t *pmd, struct vm_area_struct *vma, unsigned long addr)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	bool referenced = false;
@@ -71,13 +69,11 @@  void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr)
 	if (!folio)
 		return;
 
-	if (pmd_young(*pmd)) {
+	if (pmdp_test_and_clear_young(vma, addr, pmd))
 		referenced = true;
-		*pmd = pmd_mkold(*pmd);
-	}
 
 #ifdef CONFIG_MMU_NOTIFIER
-	if (mmu_notifier_clear_young(mm, addr, addr + HPAGE_PMD_SIZE))
+	if (mmu_notifier_clear_young(vma->vm_mm, addr, addr + HPAGE_PMD_SIZE))
 		referenced = true;
 #endif /* CONFIG_MMU_NOTIFIER */
 
diff --git a/mm/damon/ops-common.h b/mm/damon/ops-common.h
index 14f4bc69f29b..18d837d11bce 100644
--- a/mm/damon/ops-common.h
+++ b/mm/damon/ops-common.h
@@ -9,8 +9,8 @@ 
 
 struct folio *damon_get_folio(unsigned long pfn);
 
-void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr);
-void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr);
+void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr);
+void damon_pmdp_mkold(pmd_t *pmd, struct vm_area_struct *vma, unsigned long addr);
 
 int damon_cold_score(struct damon_ctx *c, struct damon_region *r,
 			struct damos *s);
diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
index 467b99166b43..5b3a3463d078 100644
--- a/mm/damon/paddr.c
+++ b/mm/damon/paddr.c
@@ -24,9 +24,9 @@  static bool __damon_pa_mkold(struct folio *folio, struct vm_area_struct *vma,
 	while (page_vma_mapped_walk(&pvmw)) {
 		addr = pvmw.address;
 		if (pvmw.pte)
-			damon_ptep_mkold(pvmw.pte, vma->vm_mm, addr);
+			damon_ptep_mkold(pvmw.pte, vma, addr);
 		else
-			damon_pmdp_mkold(pvmw.pmd, vma->vm_mm, addr);
+			damon_pmdp_mkold(pvmw.pmd, vma, addr);
 	}
 	return true;
 }
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index 1fec16d7263e..37994fb6120c 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -311,7 +311,7 @@  static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
 		}
 
 		if (pmd_trans_huge(*pmd)) {
-			damon_pmdp_mkold(pmd, walk->mm, addr);
+			damon_pmdp_mkold(pmd, walk->vma, addr);
 			spin_unlock(ptl);
 			return 0;
 		}
@@ -323,7 +323,7 @@  static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
 	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	if (!pte_present(*pte))
 		goto out;
-	damon_ptep_mkold(pte, walk->mm, addr);
+	damon_ptep_mkold(pte, walk->vma, addr);
 out:
 	pte_unmap_unlock(pte, ptl);
 	return 0;