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 that map consecutive
pages of the same large folio in a single VMA and a single page table.
While we are at it, rename the functions to maintain consistency with other
contpte_*() functions.
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
---
arch/arm64/include/asm/pgtable.h | 12 ++++++------
arch/arm64/mm/contpte.c | 33 ++++++++++++++++++--------------
2 files changed, 25 insertions(+), 20 deletions(-)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 445e18e92221..d5fbe72e820a 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1648,10 +1648,10 @@ 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);
+int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep, unsigned int nr);
+int contpte_clear_flush_young_ptes(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep, unsigned int nr);
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,
@@ -1823,7 +1823,7 @@ 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
@@ -1835,7 +1835,7 @@ 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 e4ddeb46f25d..b929a455103f 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -508,8 +508,9 @@ 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
@@ -518,41 +519,45 @@ int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma,
* contig range when the range is covered by a single folio, we can get
* away with clearing young for the whole contig range here, so we avoid
* having to unfold.
+ *
+ * The 'nr' means consecutive (present) PTEs that map consecutive pages
+ * of the same large folio in a single VMA and a single page table.
*/
+ unsigned long end = addr + nr * PAGE_SIZE;
int young = 0;
- int i;
- ptep = contpte_align_down(ptep);
- addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
-
- for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE)
+ ptep = contpte_align_addr_ptep(&addr, &end, ptep, nr);
+ for (; addr != end; ptep++, addr += PAGE_SIZE)
young |= __ptep_test_and_clear_young(vma, addr, 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 end = addr + nr * PAGE_SIZE;
+
+ contpte_align_addr_ptep(&addr, &end, ptep, nr);
/*
* See comment in __ptep_clear_flush_young(); same rationale for
* eliding the trailing DSB applies here.
*/
- addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
- __flush_tlb_range_nosync(vma->vm_mm, addr, addr + CONT_PTE_SIZE,
+ __flush_tlb_range_nosync(vma->vm_mm, addr, end,
PAGE_SIZE, true, 3);
}
return young;
}
-EXPORT_SYMBOL_GPL(contpte_ptep_clear_flush_young);
+EXPORT_SYMBOL_GPL(contpte_clear_flush_young_ptes);
void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned int nr)
--
2.47.3On 23/12/2025 05:48, 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 that map consecutive
> pages of the same large folio in a single VMA and a single page table.
>
> While we are at it, rename the functions to maintain consistency with other
> contpte_*() functions.
>
> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
> ---
> arch/arm64/include/asm/pgtable.h | 12 ++++++------
> arch/arm64/mm/contpte.c | 33 ++++++++++++++++++--------------
> 2 files changed, 25 insertions(+), 20 deletions(-)
>
> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
> index 445e18e92221..d5fbe72e820a 100644
> --- a/arch/arm64/include/asm/pgtable.h
> +++ b/arch/arm64/include/asm/pgtable.h
> @@ -1648,10 +1648,10 @@ 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);
> +int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma,
> + unsigned long addr, pte_t *ptep, unsigned int nr);
> +int contpte_clear_flush_young_ptes(struct vm_area_struct *vma,
> + unsigned long addr, pte_t *ptep, unsigned int nr);
> 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,
> @@ -1823,7 +1823,7 @@ 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);
As per your fixup patch, I agree that nr should be 1 here, not CONT_PTES.
> }
>
> #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
> @@ -1835,7 +1835,7 @@ 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);
And same here.
> }
>
> #define wrprotect_ptes wrprotect_ptes
> diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
> index e4ddeb46f25d..b929a455103f 100644
> --- a/arch/arm64/mm/contpte.c
> +++ b/arch/arm64/mm/contpte.c
> @@ -508,8 +508,9 @@ 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
> @@ -518,41 +519,45 @@ int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma,
> * contig range when the range is covered by a single folio, we can get
> * away with clearing young for the whole contig range here, so we avoid
> * having to unfold.
> + *
> + * The 'nr' means consecutive (present) PTEs that map consecutive pages
> + * of the same large folio in a single VMA and a single page table.
> */
>
> + unsigned long end = addr + nr * PAGE_SIZE;
> int young = 0;
> - int i;
>
> - ptep = contpte_align_down(ptep);
> - addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
> -
> - for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE)
> + ptep = contpte_align_addr_ptep(&addr, &end, ptep, nr);
> + for (; addr != end; ptep++, addr += PAGE_SIZE)
> young |= __ptep_test_and_clear_young(vma, addr, 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 end = addr + nr * PAGE_SIZE;
> +
> + contpte_align_addr_ptep(&addr, &end, ptep, nr);
> /*
> * See comment in __ptep_clear_flush_young(); same rationale for
> * eliding the trailing DSB applies here.
> */
> - addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
> - __flush_tlb_range_nosync(vma->vm_mm, addr, addr + CONT_PTE_SIZE,
> + __flush_tlb_range_nosync(vma->vm_mm, addr, end,
> PAGE_SIZE, true, 3);
Hmm... The requirement is that we must flush the _page_ if clearing access for a
pte that does not have the contiguous bit set, or we must flush the _contpte
block_ if clearing access for a pte that does have the contiguous bit set.
With your changes, you may call for a large range that covers multiple contpte
blocks but only has a single pte in a single contpte block for which the access
bit was previously set. But that will cause flushing the TLB for the full range.
Could this cause a performance issue? Yes, no, maybe... I think it's unlikely
but I wouldn't rule it out in some edge case.
I wonder if it's better to track the sub-ranges where access was cleared and
only issue tlbi for those sub-ranges? Probably just keep it simple (the way you
have done it) until/unless we see an actual problem?
Thanks,
Ryan
> }
>
> return young;
> }
> -EXPORT_SYMBOL_GPL(contpte_ptep_clear_flush_young);
> +EXPORT_SYMBOL_GPL(contpte_clear_flush_young_ptes);
>
> void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
> pte_t *ptep, unsigned int nr)
On 2025/12/24 22:07, Ryan Roberts wrote:
> On 23/12/2025 05:48, 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 that map consecutive
>> pages of the same large folio in a single VMA and a single page table.
>>
>> While we are at it, rename the functions to maintain consistency with other
>> contpte_*() functions.
>>
>> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
>> ---
>> arch/arm64/include/asm/pgtable.h | 12 ++++++------
>> arch/arm64/mm/contpte.c | 33 ++++++++++++++++++--------------
>> 2 files changed, 25 insertions(+), 20 deletions(-)
>>
>> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
>> index 445e18e92221..d5fbe72e820a 100644
>> --- a/arch/arm64/include/asm/pgtable.h
>> +++ b/arch/arm64/include/asm/pgtable.h
>> @@ -1648,10 +1648,10 @@ 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);
>> +int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma,
>> + unsigned long addr, pte_t *ptep, unsigned int nr);
>> +int contpte_clear_flush_young_ptes(struct vm_area_struct *vma,
>> + unsigned long addr, pte_t *ptep, unsigned int nr);
>> 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,
>> @@ -1823,7 +1823,7 @@ 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);
>
> As per your fixup patch, I agree that nr should be 1 here, not CONT_PTES.
Yes.
>> }
>>
>> #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
>> @@ -1835,7 +1835,7 @@ 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);
>
> And same here.
>
>> }
>>
>> #define wrprotect_ptes wrprotect_ptes
>> diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
>> index e4ddeb46f25d..b929a455103f 100644
>> --- a/arch/arm64/mm/contpte.c
>> +++ b/arch/arm64/mm/contpte.c
>> @@ -508,8 +508,9 @@ 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
>> @@ -518,41 +519,45 @@ int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma,
>> * contig range when the range is covered by a single folio, we can get
>> * away with clearing young for the whole contig range here, so we avoid
>> * having to unfold.
>> + *
>> + * The 'nr' means consecutive (present) PTEs that map consecutive pages
>> + * of the same large folio in a single VMA and a single page table.
>> */
>>
>> + unsigned long end = addr + nr * PAGE_SIZE;
>> int young = 0;
>> - int i;
>>
>> - ptep = contpte_align_down(ptep);
>> - addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
>> -
>> - for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE)
>> + ptep = contpte_align_addr_ptep(&addr, &end, ptep, nr);
>> + for (; addr != end; ptep++, addr += PAGE_SIZE)
>> young |= __ptep_test_and_clear_young(vma, addr, 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 end = addr + nr * PAGE_SIZE;
>> +
>> + contpte_align_addr_ptep(&addr, &end, ptep, nr);
>> /*
>> * See comment in __ptep_clear_flush_young(); same rationale for
>> * eliding the trailing DSB applies here.
>> */
>> - addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
>> - __flush_tlb_range_nosync(vma->vm_mm, addr, addr + CONT_PTE_SIZE,
>> + __flush_tlb_range_nosync(vma->vm_mm, addr, end,
>> PAGE_SIZE, true, 3);
>
> Hmm... The requirement is that we must flush the _page_ if clearing access for a
> pte that does not have the contiguous bit set, or we must flush the _contpte
> block_ if clearing access for a pte that does have the contiguous bit set.
>
> With your changes, you may call for a large range that covers multiple contpte
> blocks but only has a single pte in a single contpte block for which the access
> bit was previously set. But that will cause flushing the TLB for the full range.
> Could this cause a performance issue? Yes, no, maybe... I think it's unlikely
> but I wouldn't rule it out in some edge case.
>
> I wonder if it's better to track the sub-ranges where access was cleared and
> only issue tlbi for those sub-ranges? Probably just keep it simple (the way you
> have done it) until/unless we see an actual problem?
Good question. Indeed, as you said, we flush the TLB per folio now,
which might increase the flush range. However, I think this approach is
relatively reasonable for now.
First, the mm-core also tracks the access status per folio, and it's
really unnecessary to add excessive complexity to track the access
status of sub-pages (or sub-ranges). I can already imagine that tracking
the access status for each cont-block range as well as for non-cont
pages across the entire large folio range, which can be too complicated.
Second, __flush_tlb_range_nosync() is a lightweight flush. I quickly ran
a measurement on my machine and found that the overhead of
__flush_tlb_range_nosync() barely changes between nr=16 and nr=256 (both
are around 40 ns).
Therefore, I would still prefer to keep the logic here simple.
On 25/12/2025 02:48, Baolin Wang wrote:
>
>
> On 2025/12/24 22:07, Ryan Roberts wrote:
>> On 23/12/2025 05:48, 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 that map
>>> consecutive
>>> pages of the same large folio in a single VMA and a single page table.
>>>
>>> While we are at it, rename the functions to maintain consistency with other
>>> contpte_*() functions.
>>>
>>> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
>>> ---
>>> arch/arm64/include/asm/pgtable.h | 12 ++++++------
>>> arch/arm64/mm/contpte.c | 33 ++++++++++++++++++--------------
>>> 2 files changed, 25 insertions(+), 20 deletions(-)
>>>
>>> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
>>> index 445e18e92221..d5fbe72e820a 100644
>>> --- a/arch/arm64/include/asm/pgtable.h
>>> +++ b/arch/arm64/include/asm/pgtable.h
>>> @@ -1648,10 +1648,10 @@ 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);
>>> +int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma,
>>> + unsigned long addr, pte_t *ptep, unsigned int nr);
>>> +int contpte_clear_flush_young_ptes(struct vm_area_struct *vma,
>>> + unsigned long addr, pte_t *ptep, unsigned int nr);
>>> 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,
>>> @@ -1823,7 +1823,7 @@ 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);
>>
>> As per your fixup patch, I agree that nr should be 1 here, not CONT_PTES.
>
> Yes.
>
>>> }
>>> #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
>>> @@ -1835,7 +1835,7 @@ 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);
>>
>> And same here.
>>
>>> }
>>> #define wrprotect_ptes wrprotect_ptes
>>> diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
>>> index e4ddeb46f25d..b929a455103f 100644
>>> --- a/arch/arm64/mm/contpte.c
>>> +++ b/arch/arm64/mm/contpte.c
>>> @@ -508,8 +508,9 @@ 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
>>> @@ -518,41 +519,45 @@ int contpte_ptep_test_and_clear_young(struct
>>> vm_area_struct *vma,
>>> * contig range when the range is covered by a single folio, we can get
>>> * away with clearing young for the whole contig range here, so we avoid
>>> * having to unfold.
>>> + *
>>> + * The 'nr' means consecutive (present) PTEs that map consecutive pages
>>> + * of the same large folio in a single VMA and a single page table.
>>> */
>>> + unsigned long end = addr + nr * PAGE_SIZE;
>>> int young = 0;
>>> - int i;
>>> - ptep = contpte_align_down(ptep);
>>> - addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
>>> -
>>> - for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE)
>>> + ptep = contpte_align_addr_ptep(&addr, &end, ptep, nr);
>>> + for (; addr != end; ptep++, addr += PAGE_SIZE)
>>> young |= __ptep_test_and_clear_young(vma, addr, 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 end = addr + nr * PAGE_SIZE;
>>> +
>>> + contpte_align_addr_ptep(&addr, &end, ptep, nr);
>>> /*
>>> * See comment in __ptep_clear_flush_young(); same rationale for
>>> * eliding the trailing DSB applies here.
>>> */
>>> - addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
>>> - __flush_tlb_range_nosync(vma->vm_mm, addr, addr + CONT_PTE_SIZE,
>>> + __flush_tlb_range_nosync(vma->vm_mm, addr, end,
>>> PAGE_SIZE, true, 3);
>>
>> Hmm... The requirement is that we must flush the _page_ if clearing access for a
>> pte that does not have the contiguous bit set, or we must flush the _contpte
>> block_ if clearing access for a pte that does have the contiguous bit set.
>>
>> With your changes, you may call for a large range that covers multiple contpte
>> blocks but only has a single pte in a single contpte block for which the access
>> bit was previously set. But that will cause flushing the TLB for the full range.
>> Could this cause a performance issue? Yes, no, maybe... I think it's unlikely
>> but I wouldn't rule it out in some edge case.
>>
>> I wonder if it's better to track the sub-ranges where access was cleared and
>> only issue tlbi for those sub-ranges? Probably just keep it simple (the way you
>> have done it) until/unless we see an actual problem?
>
> Good question. Indeed, as you said, we flush the TLB per folio now, which might
> increase the flush range. However, I think this approach is relatively
> reasonable for now.
>
> First, the mm-core also tracks the access status per folio, and it's really
> unnecessary to add excessive complexity to track the access status of sub-pages
> (or sub-ranges). I can already imagine that tracking the access status for each
> cont-block range as well as for non-cont pages across the entire large folio
> range, which can be too complicated.
>
> Second, __flush_tlb_range_nosync() is a lightweight flush. I quickly ran a
> measurement on my machine and found that the overhead of
> __flush_tlb_range_nosync() barely changes between nr=16 and nr=256 (both are
> around 40 ns).
I'm not concerned about the direct cost of the flush; I agree it should be
lightweight given we elide the trailing DSB. (although there is a possible case
on older HW that doesn't support TLBI-by-range where this will be converted to
multiple TLBI-by-page instructions and that can cause stalls if there are too
many of them).
My concern was the opportunity cost of evicting the entries for all the
non-accessed parts of the folio from the TLB. But of course, I'm talking
nonsense because the architecture does not allow caching non-accessed entries in
the TLB.
So doesn't sound like a problem; I think we can ignore this. Sorry for the noise.
>
> Therefore, I would still prefer to keep the logic here simple.
Agreed.
Thanks,
Ryan
On 1/2/26 8:12 PM, Ryan Roberts wrote:
> On 25/12/2025 02:48, Baolin Wang wrote:
>>
>>
>> On 2025/12/24 22:07, Ryan Roberts wrote:
>>> On 23/12/2025 05:48, 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 that map
>>>> consecutive
>>>> pages of the same large folio in a single VMA and a single page table.
>>>>
>>>> While we are at it, rename the functions to maintain consistency with other
>>>> contpte_*() functions.
>>>>
>>>> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
>>>> ---
>>>> arch/arm64/include/asm/pgtable.h | 12 ++++++------
>>>> arch/arm64/mm/contpte.c | 33 ++++++++++++++++++--------------
>>>> 2 files changed, 25 insertions(+), 20 deletions(-)
>>>>
>>>> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
>>>> index 445e18e92221..d5fbe72e820a 100644
>>>> --- a/arch/arm64/include/asm/pgtable.h
>>>> +++ b/arch/arm64/include/asm/pgtable.h
>>>> @@ -1648,10 +1648,10 @@ 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);
>>>> +int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma,
>>>> + unsigned long addr, pte_t *ptep, unsigned int nr);
>>>> +int contpte_clear_flush_young_ptes(struct vm_area_struct *vma,
>>>> + unsigned long addr, pte_t *ptep, unsigned int nr);
>>>> 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,
>>>> @@ -1823,7 +1823,7 @@ 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);
>>>
>>> As per your fixup patch, I agree that nr should be 1 here, not CONT_PTES.
>>
>> Yes.
>>
>>>> }
>>>> #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
>>>> @@ -1835,7 +1835,7 @@ 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);
>>>
>>> And same here.
>>>
>>>> }
>>>> #define wrprotect_ptes wrprotect_ptes
>>>> diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
>>>> index e4ddeb46f25d..b929a455103f 100644
>>>> --- a/arch/arm64/mm/contpte.c
>>>> +++ b/arch/arm64/mm/contpte.c
>>>> @@ -508,8 +508,9 @@ 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
>>>> @@ -518,41 +519,45 @@ int contpte_ptep_test_and_clear_young(struct
>>>> vm_area_struct *vma,
>>>> * contig range when the range is covered by a single folio, we can get
>>>> * away with clearing young for the whole contig range here, so we avoid
>>>> * having to unfold.
>>>> + *
>>>> + * The 'nr' means consecutive (present) PTEs that map consecutive pages
>>>> + * of the same large folio in a single VMA and a single page table.
>>>> */
>>>> + unsigned long end = addr + nr * PAGE_SIZE;
>>>> int young = 0;
>>>> - int i;
>>>> - ptep = contpte_align_down(ptep);
>>>> - addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
>>>> -
>>>> - for (i = 0; i < CONT_PTES; i++, ptep++, addr += PAGE_SIZE)
>>>> + ptep = contpte_align_addr_ptep(&addr, &end, ptep, nr);
>>>> + for (; addr != end; ptep++, addr += PAGE_SIZE)
>>>> young |= __ptep_test_and_clear_young(vma, addr, 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 end = addr + nr * PAGE_SIZE;
>>>> +
>>>> + contpte_align_addr_ptep(&addr, &end, ptep, nr);
>>>> /*
>>>> * See comment in __ptep_clear_flush_young(); same rationale for
>>>> * eliding the trailing DSB applies here.
>>>> */
>>>> - addr = ALIGN_DOWN(addr, CONT_PTE_SIZE);
>>>> - __flush_tlb_range_nosync(vma->vm_mm, addr, addr + CONT_PTE_SIZE,
>>>> + __flush_tlb_range_nosync(vma->vm_mm, addr, end,
>>>> PAGE_SIZE, true, 3);
>>>
>>> Hmm... The requirement is that we must flush the _page_ if clearing access for a
>>> pte that does not have the contiguous bit set, or we must flush the _contpte
>>> block_ if clearing access for a pte that does have the contiguous bit set.
>>>
>>> With your changes, you may call for a large range that covers multiple contpte
>>> blocks but only has a single pte in a single contpte block for which the access
>>> bit was previously set. But that will cause flushing the TLB for the full range.
>>> Could this cause a performance issue? Yes, no, maybe... I think it's unlikely
>>> but I wouldn't rule it out in some edge case.
>>>
>>> I wonder if it's better to track the sub-ranges where access was cleared and
>>> only issue tlbi for those sub-ranges? Probably just keep it simple (the way you
>>> have done it) until/unless we see an actual problem?
>>
>> Good question. Indeed, as you said, we flush the TLB per folio now, which might
>> increase the flush range. However, I think this approach is relatively
>> reasonable for now.
>>
>> First, the mm-core also tracks the access status per folio, and it's really
>> unnecessary to add excessive complexity to track the access status of sub-pages
>> (or sub-ranges). I can already imagine that tracking the access status for each
>> cont-block range as well as for non-cont pages across the entire large folio
>> range, which can be too complicated.
>>
>> Second, __flush_tlb_range_nosync() is a lightweight flush. I quickly ran a
>> measurement on my machine and found that the overhead of
>> __flush_tlb_range_nosync() barely changes between nr=16 and nr=256 (both are
>> around 40 ns).
>
> I'm not concerned about the direct cost of the flush; I agree it should be
> lightweight given we elide the trailing DSB. (although there is a possible case
> on older HW that doesn't support TLBI-by-range where this will be converted to
> multiple TLBI-by-page instructions and that can cause stalls if there are too
> many of them).
>
> My concern was the opportunity cost of evicting the entries for all the
> non-accessed parts of the folio from the TLB. But of course, I'm talking
> nonsense because the architecture does not allow caching non-accessed entries in
> the TLB.
Ah, now I understand your concern:). Yes, agree.
> So doesn't sound like a problem; I think we can ignore this. Sorry for the noise.
OK. No worries.
>> Therefore, I would still prefer to keep the logic here simple.
>
> Agreed.
Thanks for your reviewing and valuable input.
Since contpte_test_and_clear_young_ptes() and contpte_clear_flush_young_ptes
have already performed CONT_PTE_SIZE alignment and will clear the young flag
for the entire cont block, Their non-batched callers do not need to pass in
'CONT_PTES' to specify the cont block range. Otherwise, it may exceed the
range of a single cont block for the non-batched cases.
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
---
Hi Andrew,
As I conducted more tests, I found that the ptep_test_and_clear_young() operation
may clear the young flag beyond a single cont block range, causing issues.
Please fold this fixup into this patch to solve this issue. Thanks.
---
arch/arm64/include/asm/pgtable.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index d5fbe72e820a..5e9ff16146c3 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1823,7 +1823,7 @@ 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_test_and_clear_young_ptes(vma, addr, ptep, CONT_PTES);
+ return contpte_test_and_clear_young_ptes(vma, addr, ptep, 1);
}
#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
@@ -1835,7 +1835,7 @@ 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_clear_flush_young_ptes(vma, addr, ptep, CONT_PTES);
+ return contpte_clear_flush_young_ptes(vma, addr, ptep, 1);
}
#define wrprotect_ptes wrprotect_ptes
--
2.47.3© 2016 - 2026 Red Hat, Inc.