[PATCH v1 18/36] mm/gup: drop nth_page() usage within folio when recording subpages

David Hildenbrand posted 36 patches 1 month ago
There is a newer version of this series
[PATCH v1 18/36] mm/gup: drop nth_page() usage within folio when recording subpages
Posted by David Hildenbrand 1 month ago
nth_page() is no longer required when iterating over pages within a
single folio, so let's just drop it when recording subpages.

Signed-off-by: David Hildenbrand <david@redhat.com>
---
 mm/gup.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index b2a78f0291273..89ca0813791ab 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -488,12 +488,11 @@ static int record_subpages(struct page *page, unsigned long sz,
 			   unsigned long addr, unsigned long end,
 			   struct page **pages)
 {
-	struct page *start_page;
 	int nr;
 
-	start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT);
+	page += (addr & (sz - 1)) >> PAGE_SHIFT;
 	for (nr = 0; addr != end; nr++, addr += PAGE_SIZE)
-		pages[nr] = nth_page(start_page, nr);
+		pages[nr] = page++;
 
 	return nr;
 }
@@ -1512,7 +1511,7 @@ static long __get_user_pages(struct mm_struct *mm,
 			}
 
 			for (j = 0; j < page_increm; j++) {
-				subpage = nth_page(page, j);
+				subpage = page + j;
 				pages[i + j] = subpage;
 				flush_anon_page(vma, subpage, start + j * PAGE_SIZE);
 				flush_dcache_page(subpage);
-- 
2.50.1
Re: [PATCH v1 18/36] mm/gup: drop nth_page() usage within folio when recording subpages
Posted by Lorenzo Stoakes 1 month ago
On Thu, Aug 28, 2025 at 12:01:22AM +0200, David Hildenbrand wrote:
> nth_page() is no longer required when iterating over pages within a
> single folio, so let's just drop it when recording subpages.
>
> Signed-off-by: David Hildenbrand <david@redhat.com>

This looks correct to me, so notwithtsanding suggestion below, LGTM and:

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

> ---
>  mm/gup.c | 7 +++----
>  1 file changed, 3 insertions(+), 4 deletions(-)
>
> diff --git a/mm/gup.c b/mm/gup.c
> index b2a78f0291273..89ca0813791ab 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -488,12 +488,11 @@ static int record_subpages(struct page *page, unsigned long sz,
>  			   unsigned long addr, unsigned long end,
>  			   struct page **pages)
>  {
> -	struct page *start_page;
>  	int nr;
>
> -	start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT);
> +	page += (addr & (sz - 1)) >> PAGE_SHIFT;
>  	for (nr = 0; addr != end; nr++, addr += PAGE_SIZE)
> -		pages[nr] = nth_page(start_page, nr);
> +		pages[nr] = page++;


This is really nice, but I wonder if (while we're here) we can't be even
more clear as to what's going on here, e.g.:

static int record_subpages(struct page *page, unsigned long sz,
			   unsigned long addr, unsigned long end,
			   struct page **pages)
{
	size_t offset_in_folio = (addr & (sz - 1)) >> PAGE_SHIFT;
	struct page *subpage = page + offset_in_folio;

	for (; addr != end; addr += PAGE_SIZE)
		*pages++ = subpage++;

	return nr;
}

Or some variant of that with the masking stuff self-documented.

>
>  	return nr;
>  }
> @@ -1512,7 +1511,7 @@ static long __get_user_pages(struct mm_struct *mm,
>  			}
>
>  			for (j = 0; j < page_increm; j++) {
> -				subpage = nth_page(page, j);
> +				subpage = page + j;
>  				pages[i + j] = subpage;
>  				flush_anon_page(vma, subpage, start + j * PAGE_SIZE);
>  				flush_dcache_page(subpage);
> --
> 2.50.1
>

Cheers, Lorenzo
Re: [PATCH v1 18/36] mm/gup: drop nth_page() usage within folio when recording subpages
Posted by David Hildenbrand 1 month ago
On 28.08.25 18:37, Lorenzo Stoakes wrote:
> On Thu, Aug 28, 2025 at 12:01:22AM +0200, David Hildenbrand wrote:
>> nth_page() is no longer required when iterating over pages within a
>> single folio, so let's just drop it when recording subpages.
>>
>> Signed-off-by: David Hildenbrand <david@redhat.com>
> 
> This looks correct to me, so notwithtsanding suggestion below, LGTM and:
> 
> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
> 
>> ---
>>   mm/gup.c | 7 +++----
>>   1 file changed, 3 insertions(+), 4 deletions(-)
>>
>> diff --git a/mm/gup.c b/mm/gup.c
>> index b2a78f0291273..89ca0813791ab 100644
>> --- a/mm/gup.c
>> +++ b/mm/gup.c
>> @@ -488,12 +488,11 @@ static int record_subpages(struct page *page, unsigned long sz,
>>   			   unsigned long addr, unsigned long end,
>>   			   struct page **pages)
>>   {
>> -	struct page *start_page;
>>   	int nr;
>>
>> -	start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT);
>> +	page += (addr & (sz - 1)) >> PAGE_SHIFT;
>>   	for (nr = 0; addr != end; nr++, addr += PAGE_SIZE)
>> -		pages[nr] = nth_page(start_page, nr);
>> +		pages[nr] = page++;
> 
> 
> This is really nice, but I wonder if (while we're here) we can't be even
> more clear as to what's going on here, e.g.:
> 
> static int record_subpages(struct page *page, unsigned long sz,
> 			   unsigned long addr, unsigned long end,
> 			   struct page **pages)
> {
> 	size_t offset_in_folio = (addr & (sz - 1)) >> PAGE_SHIFT;
> 	struct page *subpage = page + offset_in_folio;
> 
> 	for (; addr != end; addr += PAGE_SIZE)
> 		*pages++ = subpage++;
> 
> 	return nr;
> }
> 
> Or some variant of that with the masking stuff self-documented.

What about the following cleanup on top:


diff --git a/mm/gup.c b/mm/gup.c
index 89ca0813791ab..5a72a135ec70b 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -484,19 +484,6 @@ static inline void mm_set_has_pinned_flag(struct mm_struct *mm)
  #ifdef CONFIG_MMU
  
  #ifdef CONFIG_HAVE_GUP_FAST
-static int record_subpages(struct page *page, unsigned long sz,
-                          unsigned long addr, unsigned long end,
-                          struct page **pages)
-{
-       int nr;
-
-       page += (addr & (sz - 1)) >> PAGE_SHIFT;
-       for (nr = 0; addr != end; nr++, addr += PAGE_SIZE)
-               pages[nr] = page++;
-
-       return nr;
-}
-
  /**
   * try_grab_folio_fast() - Attempt to get or pin a folio in fast path.
   * @page:  pointer to page to be grabbed
@@ -2963,8 +2950,8 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
         if (pmd_special(orig))
                 return 0;
  
-       page = pmd_page(orig);
-       refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr);
+       refs = (end - addr) >> PAGE_SHIFT;
+       page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
  
         folio = try_grab_folio_fast(page, refs, flags);
         if (!folio)
@@ -2985,6 +2972,8 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
         }
  
         *nr += refs;
+       for (; refs; refs--)
+               *(pages++) = page++;
         folio_set_referenced(folio);
         return 1;
  }
@@ -3003,8 +2992,8 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
         if (pud_special(orig))
                 return 0;
  
-       page = pud_page(orig);
-       refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr);
+       refs = (end - addr) >> PAGE_SHIFT;
+       page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
  
         folio = try_grab_folio_fast(page, refs, flags);
         if (!folio)
@@ -3026,6 +3015,8 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
         }
  
         *nr += refs;
+       for (; refs; refs--)
+               *(pages++) = page++;
         folio_set_referenced(folio);
         return 1;
  }


The nice thing is that we only record pages in the array if they actually passed our tests.


-- 
Cheers

David / dhildenb
Re: [PATCH v1 18/36] mm/gup: drop nth_page() usage within folio when recording subpages
Posted by Lorenzo Stoakes 1 month ago
On Fri, Aug 29, 2025 at 03:41:40PM +0200, David Hildenbrand wrote:
> On 28.08.25 18:37, Lorenzo Stoakes wrote:
> > On Thu, Aug 28, 2025 at 12:01:22AM +0200, David Hildenbrand wrote:
> > > nth_page() is no longer required when iterating over pages within a
> > > single folio, so let's just drop it when recording subpages.
> > >
> > > Signed-off-by: David Hildenbrand <david@redhat.com>
> >
> > This looks correct to me, so notwithtsanding suggestion below, LGTM and:
> >
> > Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
> >
> > > ---
> > >   mm/gup.c | 7 +++----
> > >   1 file changed, 3 insertions(+), 4 deletions(-)
> > >
> > > diff --git a/mm/gup.c b/mm/gup.c
> > > index b2a78f0291273..89ca0813791ab 100644
> > > --- a/mm/gup.c
> > > +++ b/mm/gup.c
> > > @@ -488,12 +488,11 @@ static int record_subpages(struct page *page, unsigned long sz,
> > >   			   unsigned long addr, unsigned long end,
> > >   			   struct page **pages)
> > >   {
> > > -	struct page *start_page;
> > >   	int nr;
> > >
> > > -	start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT);
> > > +	page += (addr & (sz - 1)) >> PAGE_SHIFT;
> > >   	for (nr = 0; addr != end; nr++, addr += PAGE_SIZE)
> > > -		pages[nr] = nth_page(start_page, nr);
> > > +		pages[nr] = page++;
> >
> >
> > This is really nice, but I wonder if (while we're here) we can't be even
> > more clear as to what's going on here, e.g.:
> >
> > static int record_subpages(struct page *page, unsigned long sz,
> > 			   unsigned long addr, unsigned long end,
> > 			   struct page **pages)
> > {
> > 	size_t offset_in_folio = (addr & (sz - 1)) >> PAGE_SHIFT;
> > 	struct page *subpage = page + offset_in_folio;
> >
> > 	for (; addr != end; addr += PAGE_SIZE)
> > 		*pages++ = subpage++;
> >
> > 	return nr;
> > }
> >
> > Or some variant of that with the masking stuff self-documented.
>
> What about the following cleanup on top:
>
>
> diff --git a/mm/gup.c b/mm/gup.c
> index 89ca0813791ab..5a72a135ec70b 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -484,19 +484,6 @@ static inline void mm_set_has_pinned_flag(struct mm_struct *mm)
>  #ifdef CONFIG_MMU
>  #ifdef CONFIG_HAVE_GUP_FAST
> -static int record_subpages(struct page *page, unsigned long sz,
> -                          unsigned long addr, unsigned long end,
> -                          struct page **pages)
> -{
> -       int nr;
> -
> -       page += (addr & (sz - 1)) >> PAGE_SHIFT;
> -       for (nr = 0; addr != end; nr++, addr += PAGE_SIZE)
> -               pages[nr] = page++;
> -
> -       return nr;
> -}
> -
>  /**
>   * try_grab_folio_fast() - Attempt to get or pin a folio in fast path.
>   * @page:  pointer to page to be grabbed
> @@ -2963,8 +2950,8 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
>         if (pmd_special(orig))
>                 return 0;
> -       page = pmd_page(orig);
> -       refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr);
> +       refs = (end - addr) >> PAGE_SHIFT;
> +       page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);

Ah I see we use page_folio() in try_grab_folio_fast() so this being within PMD is ok.

>         folio = try_grab_folio_fast(page, refs, flags);
>         if (!folio)
> @@ -2985,6 +2972,8 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
>         }
>         *nr += refs;
> +       for (; refs; refs--)
> +               *(pages++) = page++;
>         folio_set_referenced(folio);
>         return 1;
>  }
> @@ -3003,8 +2992,8 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
>         if (pud_special(orig))
>                 return 0;
> -       page = pud_page(orig);
> -       refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr);
> +       refs = (end - addr) >> PAGE_SHIFT;
> +       page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
>         folio = try_grab_folio_fast(page, refs, flags);
>         if (!folio)
> @@ -3026,6 +3015,8 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
>         }
>         *nr += refs;
> +       for (; refs; refs--)
> +               *(pages++) = page++;
>         folio_set_referenced(folio);
>         return 1;
>  }
>
>
> The nice thing is that we only record pages in the array if they actually passed our tests.

Yeah that's nice actually.

This is fine (not the meme :P)

So yes let's do this!

>
>
> --
> Cheers
>
> David / dhildenb
>

Cheers, Lorenzo
Re: [PATCH v1 18/36] mm/gup: drop nth_page() usage within folio when recording subpages
Posted by David Hildenbrand 1 month ago
>>
>>
>> The nice thing is that we only record pages in the array if they actually passed our tests.
> 
> Yeah that's nice actually.
> 
> This is fine (not the meme :P)

:D

> 
> So yes let's do this!

That leaves us with the following on top of this patch:

 From 4533c6e3590cab0c53e81045624d5949e0ad9015 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 29 Aug 2025 15:41:45 +0200
Subject: [PATCH] mm/gup: remove record_subpages()

We can just cleanup the code by calculating the #refs earlier,
so we can just inline what remains of record_subpages().

Calculate the number of references/pages ahead of times, and record them
only once all our tests passed.

Signed-off-by: David Hildenbrand <david@redhat.com>
---
  mm/gup.c | 25 ++++++++-----------------
  1 file changed, 8 insertions(+), 17 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 89ca0813791ab..5a72a135ec70b 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -484,19 +484,6 @@ static inline void mm_set_has_pinned_flag(struct mm_struct *mm)
  #ifdef CONFIG_MMU
  
  #ifdef CONFIG_HAVE_GUP_FAST
-static int record_subpages(struct page *page, unsigned long sz,
-			   unsigned long addr, unsigned long end,
-			   struct page **pages)
-{
-	int nr;
-
-	page += (addr & (sz - 1)) >> PAGE_SHIFT;
-	for (nr = 0; addr != end; nr++, addr += PAGE_SIZE)
-		pages[nr] = page++;
-
-	return nr;
-}
-
  /**
   * try_grab_folio_fast() - Attempt to get or pin a folio in fast path.
   * @page:  pointer to page to be grabbed
@@ -2963,8 +2950,8 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
  	if (pmd_special(orig))
  		return 0;
  
-	page = pmd_page(orig);
-	refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr);
+	refs = (end - addr) >> PAGE_SHIFT;
+	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
  
  	folio = try_grab_folio_fast(page, refs, flags);
  	if (!folio)
@@ -2985,6 +2972,8 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
  	}
  
  	*nr += refs;
+	for (; refs; refs--)
+		*(pages++) = page++;
  	folio_set_referenced(folio);
  	return 1;
  }
@@ -3003,8 +2992,8 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
  	if (pud_special(orig))
  		return 0;
  
-	page = pud_page(orig);
-	refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr);
+	refs = (end - addr) >> PAGE_SHIFT;
+	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
  
  	folio = try_grab_folio_fast(page, refs, flags);
  	if (!folio)
@@ -3026,6 +3015,8 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
  	}
  
  	*nr += refs;
+	for (; refs; refs--)
+		*(pages++) = page++;
  	folio_set_referenced(folio);
  	return 1;
  }
-- 
2.50.1


-- 
Cheers

David / dhildenb