| 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: <d3b40df8-e5cf-42aa-8205-de624024fad1@arm.com>
Date: Thu, 18 Dec 2025 12:20:13 +0000
From: Ryan Roberts <ryan.roberts@....com>
To: Baolin Wang <baolin.wang@...ux.alibaba.com>, akpm@...ux-foundation.org,
david@...nel.org, catalin.marinas@....com, will@...nel.org
Cc: lorenzo.stoakes@...cle.com, Liam.Howlett@...cle.com, vbabka@...e.cz,
rppt@...nel.org, surenb@...gle.com, mhocko@...e.com, riel@...riel.com,
harry.yoo@...cle.com, jannh@...gle.com, willy@...radead.org,
baohua@...nel.org, linux-mm@...ck.org, linux-arm-kernel@...ts.infradead.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2 1/3] arm64: mm: support batch clearing of the young
flag for large folios
On 18/12/2025 07:15, Baolin Wang wrote:
>
>
> On 2025/12/17 23:43, Ryan Roberts wrote:
>> Sorry I'm a bit late to the party...
>
> Never mind. It's not late and comments are always welcome :)
>
>> On 11/12/2025 08:16, Baolin Wang wrote:
>>> Currently, contpte_ptep_test_and_clear_young() and
>>> contpte_ptep_clear_flush_young()
>>> only clear the young flag and flush TLBs for PTEs within the contiguous range.
>>> To support batch PTE operations for other sized large folios in the following
>>> patches, adding a new parameter to specify the number of PTEs.
>>>
>>> While we are at it, rename the functions to maintain consistency with other
>>> contpte_*() functions.
>>>
>>> Signed-off-by: Baolin Wang <baolin.wang@...ux.alibaba.com>
>>> ---
>>> arch/arm64/include/asm/pgtable.h | 12 ++++-----
>>> arch/arm64/mm/contpte.c | 44 ++++++++++++++++++++++----------
>>> 2 files changed, 37 insertions(+), 19 deletions(-)
>>>
>>> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
>>> index 0944e296dd4a..e03034683156 100644
>>> --- a/arch/arm64/include/asm/pgtable.h
>>> +++ b/arch/arm64/include/asm/pgtable.h
>>> @@ -1679,10 +1679,10 @@ extern void contpte_clear_full_ptes(struct mm_struct
>>> *mm, unsigned long addr,
>>> extern pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm,
>>> unsigned long addr, pte_t *ptep,
>>> unsigned int nr, int full);
>>> -extern int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma,
>>> - unsigned long addr, pte_t *ptep);
>>> -extern int contpte_ptep_clear_flush_young(struct vm_area_struct *vma,
>>> - unsigned long addr, pte_t *ptep);
>>> +extern int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma,
>>> + unsigned long addr, pte_t *ptep, unsigned int nr);
>>> +extern int contpte_clear_flush_young_ptes(struct vm_area_struct *vma,
>>> + unsigned long addr, pte_t *ptep, unsigned int nr);
>>
>> The "contpte_" functions are intended to be private to the arm64 arch and should
>> be exposed via the generic APIs. But I don't see any generic batched API for
>> this, so you're only actually able to pass CONT_PTES as nr. Perhaps you're
>> planning to define "test_and_clear_young_ptes()" and "clear_flush_young_ptes()"
>> in later patches?
>
> Right. This is a preparation patch, and will be used in patch 2.
>
>>> extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
>>> pte_t *ptep, unsigned int nr);
>>> extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
>>> @@ -1854,7 +1854,7 @@ static inline int ptep_test_and_clear_young(struct
>>> vm_area_struct *vma,
>>> if (likely(!pte_valid_cont(orig_pte)))
>>> return __ptep_test_and_clear_young(vma, addr, ptep);
>>> - return contpte_ptep_test_and_clear_young(vma, addr, ptep);
>>> + return contpte_test_and_clear_young_ptes(vma, addr, ptep, CONT_PTES);
>>> }
>>> #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
>>> @@ -1866,7 +1866,7 @@ static inline int ptep_clear_flush_young(struct
>>> vm_area_struct *vma,
>>> if (likely(!pte_valid_cont(orig_pte)))
>>> return __ptep_clear_flush_young(vma, addr, ptep);
>>> - return contpte_ptep_clear_flush_young(vma, addr, ptep);
>>> + return contpte_clear_flush_young_ptes(vma, addr, ptep, CONT_PTES);
>>> }
>>> #define wrprotect_ptes wrprotect_ptes
>>> diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
>>> index c0557945939c..19b122441be3 100644
>>> --- a/arch/arm64/mm/contpte.c
>>> +++ b/arch/arm64/mm/contpte.c
>>> @@ -488,8 +488,9 @@ pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm,
>>> }
>>> EXPORT_SYMBOL_GPL(contpte_get_and_clear_full_ptes);
>>> -int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma,
>>> - unsigned long addr, pte_t *ptep)
>>> +int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma,
>>> + unsigned long addr, pte_t *ptep,
>>> + unsigned int nr)
>>> {
>>> /*
>>> * ptep_clear_flush_young() technically requires us to clear the access
>>> @@ -500,39 +501,56 @@ int contpte_ptep_test_and_clear_young(struct
>>> vm_area_struct *vma,
>>> * having to unfold.
>>> */
>>> + unsigned long start = addr;
>>
>> Personally I wouldn't bother defining start - just reuse addr. You're
>> incrementing start in the below loop, so it's more appropriate to call it addr
>> anyway.
>
> OK.
>
>>> + unsigned long end = start + nr * PAGE_SIZE;
>>> int young = 0;
>>> int i;
>>> - ptep = contpte_align_down(ptep);
>>> - addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
>>> + if (pte_cont(__ptep_get(ptep + nr - 1)))
>>> + end = ALIGN(end, CONT_PTE_SIZE);
>>> - for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE)
>>> - young |= __ptep_test_and_clear_young(vma, addr, ptep);
>>> + if (pte_cont(__ptep_get(ptep))) {
>>> + start = ALIGN_DOWN(start, CONT_PTE_SIZE);
>>> + ptep = contpte_align_down(ptep);
>>> + }
>>> +
>>> + nr = (end - start) / PAGE_SIZE;
>>> + for (i = 0; i < nr; i++, ptep++, start += PAGE_SIZE)
>>
>> Given you're now defining end, perhaps we don't need nr?
>>
>> for (; addr != end; ptep++, addr += PAGE_SIZE)
>> young |= __ptep_test_and_clear_young(vma, addr, ptep);
>
> Yes, good point.
>
>>> + young |= __ptep_test_and_clear_young(vma, start, ptep);
>>> return young;
>>> }
>>> -EXPORT_SYMBOL_GPL(contpte_ptep_test_and_clear_young);
>>> +EXPORT_SYMBOL_GPL(contpte_test_and_clear_young_ptes);
>>> -int contpte_ptep_clear_flush_young(struct vm_area_struct *vma,
>>> - unsigned long addr, pte_t *ptep)
>>> +int contpte_clear_flush_young_ptes(struct vm_area_struct *vma,
>>> + unsigned long addr, pte_t *ptep,
>>> + unsigned int nr)
>>> {
>>> int young;
>>> - young = contpte_ptep_test_and_clear_young(vma, addr, ptep);
>>> + young = contpte_test_and_clear_young_ptes(vma, addr, ptep, nr);
>>> if (young) {
>>> + unsigned long start = addr;
>>> + unsigned long end = start + nr * PAGE_SIZE;
>>> +
>>> + if (pte_cont(__ptep_get(ptep + nr - 1)))
>>> + end = ALIGN(end, CONT_PTE_SIZE);
>>> +
>>> + if (pte_cont(__ptep_get(ptep)))
>>> + start = ALIGN_DOWN(start, CONT_PTE_SIZE);
>>> +
>>
>> We now have this pattern of expanding contpte blocks up and down in 3 places.
>> Perhaps create a helper?
>
> Sounds reasonable. How about the following helper?
>
> static pte_t *contpte_align_addr_ptep(unsigned long *start, unsigned long *end,
> pte_t *ptep, unsigned int nr)
> {
> unsigned long end_addr = *start + nr * PAGE_SIZE;
>
> if (pte_cont(__ptep_get(ptep + nr - 1)))
I think this is safe but calling it out to check; you're not checking that the
pte is valid, so theoretically you could have a swap-entry here with whatever
overlays the contiguous bit set. So then you would incorrectly extend.
But I think it is safe because the expectation is that core-mm has already
checked that the whole range is present?
> *end = ALIGN(end_addr, CONT_PTE_SIZE);
>
> if (pte_cont(__ptep_get(ptep))) {
> *start = ALIGN_DOWN(*start, CONT_PTE_SIZE);
> ptep = contpte_align_down(ptep);
> }
>
> return ptep;
> }
Looks good.
Powered by blists - more mailing lists