Re: [PATCH RFC v2 11/18] mm: skip zeroing in vma_alloc_zeroed_movable_folio for pre-zeroed pages

["David Hildenbrand (Arm)" <david@kernel.org>]

On 4/21/26 13:12, David Hildenbrand (Arm) wrote:
> On 4/21/26 12:58, David Hildenbrand (Arm) wrote:
>> On 4/20/26 14:50, Michael S. Tsirkin wrote:
>>> Use vma_alloc_folio_hints() and check PGHINT_ZEROED to skip
>>> clear_user_highpage() when the page is already zeroed.
>>>
>>> On x86, vma_alloc_zeroed_movable_folio is overridden by a macro
>>> that uses __GFP_ZERO directly, so this change has no effect there.
>>>
>>> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
>>> Assisted-by: Claude:claude-opus-4-6
>>> Assisted-by: cursor-agent:GPT-5.4-xhigh
>>> ---
>>>  include/linux/highmem.h | 6 ++++--
>>>  1 file changed, 4 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/include/linux/highmem.h b/include/linux/highmem.h
>>> index af03db851a1d..8bb67772c1cb 100644
>>> --- a/include/linux/highmem.h
>>> +++ b/include/linux/highmem.h
>>> @@ -321,9 +321,11 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma,
>>>  				   unsigned long vaddr)
>>>  {
>>>  	struct folio *folio;
>>> +	pghint_t hints;
>>>  
>>> -	folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr);
>>> -	if (folio && user_alloc_needs_zeroing())
>>> +	folio = vma_alloc_folio_hints(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr,
>>> +				      &hints);
>>> +	if (folio && user_alloc_needs_zeroing() && !(hints & PGHINT_ZEROED))
>>>  		clear_user_highpage(&folio->page, vaddr);
>>>  
>>>  	return folio;
>>
>>
>> For others reading along, the variant on your other branch:
>>
>> diff --git a/include/linux/highmem.h b/include/linux/highmem.h
>> index af03db851a1d9..ffa683f64f1d1 100644
>> --- a/include/linux/highmem.h
>> +++ b/include/linux/highmem.h
>> @@ -320,13 +320,8 @@ static inline
>>  struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma,
>>  				   unsigned long vaddr)
>>  {
>> -	struct folio *folio;
>> -
>> -	folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr);
>> -	if (folio && user_alloc_needs_zeroing())
>> -		clear_user_highpage(&folio->page, vaddr);
>> -
>> -	return folio;
>> +	return vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO,
>> +			      0, vma, vaddr);
>>  }
>>  #endif
>>
>> Looks like an extremely clean interface.
>>
> 
> And we could likely just do the following on top I assume.
> 
> diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h
> index d2532bc407ef..f511b763a235 100644
> --- a/arch/m68k/include/asm/page_no.h
> +++ b/arch/m68k/include/asm/page_no.h
> @@ -12,9 +12,6 @@ extern unsigned long memory_end;
>  
>  #define copy_user_page(to, from, vaddr, pg)    copy_page(to, from)
>  
> -#define vma_alloc_zeroed_movable_folio(vma, vaddr) \
> -       vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr)
> -
>  #define __pa(vaddr)            ((unsigned long)(vaddr))
>  #define __va(paddr)            ((void *)((unsigned long)(paddr)))
>  
> diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
> index 56da819a79e6..e995d2a413f9 100644
> --- a/arch/s390/include/asm/page.h
> +++ b/arch/s390/include/asm/page.h
> @@ -67,9 +67,6 @@ static inline void copy_page(void *to, void *from)
>  
>  #define copy_user_page(to, from, vaddr, pg)    copy_page(to, from)
>  
> -#define vma_alloc_zeroed_movable_folio(vma, vaddr) \
> -       vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr)
> -
>  #ifdef CONFIG_STRICT_MM_TYPECHECKS
>  #define STRICT_MM_TYPECHECKS
>  #endif
> diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
> index 416dc88e35c1..92fa975b46f3 100644
> --- a/arch/x86/include/asm/page.h
> +++ b/arch/x86/include/asm/page.h
> @@ -28,9 +28,6 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
>         copy_page(to, from);
>  }
>  
> -#define vma_alloc_zeroed_movable_folio(vma, vaddr) \
> -       vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr)
> -
>  #ifndef __pa
>  #define __pa(x)                __phys_addr((unsigned long)(x))
>  #endif
> 
> 

... and I wonder whether we could then convert the arm64 variant into a
simple helper that just returns additional gfp flags.

We might even be able to call that from inside vma_alloc_folio(), to
just get __GFP_ZEROTAGS whenever the VMA has VM_MTE.

But that's obviously some additional work on top.

-- 
Cheers,

David