Re: [PATCH v4 3/3] vfio/type1: optimize vfio_unpin_pages_remote() for large folio

[lizhe.67@bytedance.com]

On Wed, 18 Jun 2025 10:54:38 +0200, david@redhat.com wrote:
 
> On 18.06.25 08:11, lizhe.67@bytedance.com wrote:
> > On Tue, 17 Jun 2025 15:47:09 +0200, david@redhat.com wrote:
> >   
> >>> How do you think of this implementation?
> >>>
> >>> diff --git a/include/linux/mm.h b/include/linux/mm.h
> >>> index 242b05671502..eb91f99ea973 100644
> >>> --- a/include/linux/mm.h
> >>> +++ b/include/linux/mm.h
> >>> @@ -2165,6 +2165,23 @@ static inline long folio_nr_pages(const struct folio *folio)
> >>>           return folio_large_nr_pages(folio);
> >>>    }
> >>>    
> >>> +/*
> >>> + * folio_remaining_pages - Counts the number of pages from a given
> >>> + * start page to the end of the folio.
> >>> + *
> >>> + * @folio: Pointer to folio
> >>> + * @start_page: The starting page from which to begin counting.
> >>> + *
> >>> + * Returned number includes the provided start page.
> >>> + *
> >>> + * The caller must ensure that @start_page belongs to @folio.
> >>> + */
> >>> +static inline unsigned long folio_remaining_pages(struct folio *folio,
> >>> +               struct page *start_page)
> >>> +{
> >>> +       return folio_nr_pages(folio) - folio_page_idx(folio, start_page);
> >>> +}
> >>> +
> >>>    /* Only hugetlbfs can allocate folios larger than MAX_ORDER */
> >>>    #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
> >>>    #define MAX_FOLIO_NR_PAGES     (1UL << PUD_ORDER)
> >>> diff --git a/mm/gup.c b/mm/gup.c
> >>> index 15debead5f5b..14ae2e3088b4 100644
> >>> --- a/mm/gup.c
> >>> +++ b/mm/gup.c
> >>> @@ -242,7 +242,7 @@ static inline struct folio *gup_folio_range_next(struct page *start,
> >>>    
> >>>           if (folio_test_large(folio))
> >>>                   nr = min_t(unsigned int, npages - i,
> >>> -                          folio_nr_pages(folio) - folio_page_idx(folio, next));
> >>> +                          folio_remaining_pages(folio, next));
> >>>    
> >>>           *ntails = nr;
> >>>           return folio;
> >>> diff --git a/mm/page_isolation.c b/mm/page_isolation.c
> >>> index b2fc5266e3d2..34e85258060c 100644
> >>> --- a/mm/page_isolation.c
> >>> +++ b/mm/page_isolation.c
> >>> @@ -96,7 +96,7 @@ static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long e
> >>>                                   return page;
> >>>                           }
> >>>    
> >>> -                       skip_pages = folio_nr_pages(folio) - folio_page_idx(folio, page);
> >>> +                       skip_pages = folio_remaining_pages(folio, page);
> >>>                           pfn += skip_pages - 1;
> >>>                           continue;
> >>>                   }
> >>> ---
> >>
> >> Guess I would have pulled the "min" in there, but passing something like
> >> ULONG_MAX for the page_isolation case also looks rather ugly.
> > 
> > Yes, the page_isolation case does not require the 'min' logic. Since
> > there are already places in the current kernel code where
> > folio_remaining_pages() is used without needing min, we could simply
> > create a custom wrapper function based on folio_remaining_pages() only
> > in those specific scenarios where min is necessary.
> 
> I would just do something like that, removing gup_folio_range_next() completely.
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 98a606908307b..6c224b1c6c169 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1995,6 +1995,32 @@ static inline long folio_nr_pages(const struct folio *folio)
>   	return folio_large_nr_pages(folio);
>   }
>   
> +/**
> + * folio_remaining_pages - The remaining number of pages in the folio.
> + * @folio: The folio.
> + * @page: The folio page to start the counting.
> + * @max_npages: Limit how far to count.
> + *
> + * The returned number will include the provided page.
> + *
> + * The caller must ensure that @page belongs to @folio. When setting
> + * @max_npages to ULONG_MAX, the parameter is effectively ignored.
> + *
> + * Return: The remaining number of pages, limited by @max_npages.
> + */
> +static inline unsigned long folio_remaining_pages(struct folio *folio,
> +		struct page *page, unsigned long max_npages)
> +{
> +	unsigned long nr;
> +
> +	if (!folio_test_large(folio))
> +		return 1;
> +	nr = folio_large_nr_pages(folio) - folio_page_idx(folio, page);
> +	if (__builtin_constant_p(max_npages) && max_npages == ULONG_MAX)
> +		return nr;
> +	return min_t(unsigned long, nr, max_npages);
> +}
> +
>   /* Only hugetlbfs can allocate folios larger than MAX_ORDER */
>   #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
>   #define MAX_FOLIO_NR_PAGES	(1UL << PUD_ORDER)
> diff --git a/mm/gup.c b/mm/gup.c
> index 6888e871a74a9..3385428d028f6 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -234,21 +234,6 @@ void folio_add_pin(struct folio *folio)
>   	}
>   }
>   
> -static inline struct folio *gup_folio_range_next(struct page *start,
> -		unsigned long npages, unsigned long i, unsigned int *ntails)
> -{
> -	struct page *next = nth_page(start, i);
> -	struct folio *folio = page_folio(next);
> -	unsigned int nr = 1;
> -
> -	if (folio_test_large(folio))
> -		nr = min_t(unsigned int, npages - i,
> -			   folio_nr_pages(folio) - folio_page_idx(folio, next));
> -
> -	*ntails = nr;
> -	return folio;
> -}
> -
>   static inline struct folio *gup_folio_next(struct page **list,
>   		unsigned long npages, unsigned long i, unsigned int *ntails)
>   {
> @@ -356,11 +341,13 @@ void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
>   				      bool make_dirty)
>   {
>   	unsigned long i;
> -	struct folio *folio;
>   	unsigned int nr;
>   
>   	for (i = 0; i < npages; i += nr) {
> -		folio = gup_folio_range_next(page, npages, i, &nr);
> +		struct page *next = nth_page(page, i);
> +		struct folio *folio = page_folio(next);
> +
> +		nr = folio_remaining_pages(folio, next, npages - i);
>   		if (make_dirty && !folio_test_dirty(folio)) {
>   			folio_lock(folio);
>   			folio_mark_dirty(folio);
> diff --git a/mm/page_isolation.c b/mm/page_isolation.c
> index ece3bfc56bcd5..6f75defb38d73 100644
> --- a/mm/page_isolation.c
> +++ b/mm/page_isolation.c
> @@ -96,7 +96,7 @@ static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long e
>   				return page;
>   			}
>   
> -			skip_pages = folio_nr_pages(folio) - folio_page_idx(folio, page);
> +			skip_pages = folio_remaining_pages(folio, page, ULONG_MAX);
>   			pfn += skip_pages - 1;
>   			continue;
>   		}
> -- 
> 
> 
> But up to you, anything with such a helper function makes the code easier to digest.

Thank you. This implementation looks better. Please allow me to
integrate this patch into my patchset.

Thanks,
Zhe