On 15/03/2023 05:14, Matthew Wilcox (Oracle) wrote:
> From: Yin Fengwei <fengwei.yin@xxxxxxxxx>
>
> folio_add_file_rmap_range() allows to add pte mapping to a specific
> range of file folio. Comparing to page_add_file_rmap(), it batched
> updates __lruvec_stat for large folio.
>
> Signed-off-by: Yin Fengwei <fengwei.yin@xxxxxxxxx>
> Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
> ---
> include/linux/rmap.h | 2 ++
> mm/rmap.c | 60 +++++++++++++++++++++++++++++++++-----------
> 2 files changed, 48 insertions(+), 14 deletions(-)
>
> diff --git a/include/linux/rmap.h b/include/linux/rmap.h
> index b87d01660412..a3825ce81102 100644
> --- a/include/linux/rmap.h
> +++ b/include/linux/rmap.h
> @@ -198,6 +198,8 @@ void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *,
> unsigned long address);
> void page_add_file_rmap(struct page *, struct vm_area_struct *,
> bool compound);
> +void folio_add_file_rmap_range(struct folio *, struct page *, unsigned int nr,
> + struct vm_area_struct *, bool compound);
> void page_remove_rmap(struct page *, struct vm_area_struct *,
> bool compound);
>
> diff --git a/mm/rmap.c b/mm/rmap.c
> index 4898e10c569a..a91906b28835 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -1301,31 +1301,39 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
> }
>
> /**
> - * page_add_file_rmap - add pte mapping to a file page
> - * @page: the page to add the mapping to
> + * folio_add_file_rmap_range - add pte mapping to page range of a folio
> + * @folio: The folio to add the mapping to
> + * @page: The first page to add
> + * @nr_pages: The number of pages which will be mapped
> * @vma: the vm area in which the mapping is added
> * @compound: charge the page as compound or small page
> *
> + * The page range of folio is defined by [first_page, first_page + nr_pages)
> + *
> * The caller needs to hold the pte lock.
> */
> -void page_add_file_rmap(struct page *page, struct vm_area_struct *vma,
> - bool compound)
> +void folio_add_file_rmap_range(struct folio *folio, struct page *page,
> + unsigned int nr_pages, struct vm_area_struct *vma,
> + bool compound)
> {
> - struct folio *folio = page_folio(page);
> atomic_t *mapped = &folio->_nr_pages_mapped;
> - int nr = 0, nr_pmdmapped = 0;
> - bool first;
> + unsigned int nr_pmdmapped = 0, first;
> + int nr = 0;
>
> - VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page);
> + VM_WARN_ON_FOLIO(compound && !folio_test_pmd_mappable(folio), folio);
>
> /* Is page being mapped by PTE? Is this its first map to be added? */
> if (likely(!compound)) {
> - first = atomic_inc_and_test(&page->_mapcount);
> - nr = first;
> - if (first && folio_test_large(folio)) {
> - nr = atomic_inc_return_relaxed(mapped);
> - nr = (nr < COMPOUND_MAPPED);
> - }
> + do {
> + first = atomic_inc_and_test(&page->_mapcount);
> + if (first && folio_test_large(folio)) {
> + first = atomic_inc_return_relaxed(mapped);
> + first = (nr < COMPOUND_MAPPED);
This still contains the typo that Yin Fengwei spotted in the previous version:
https://lore.kernel.org/linux-mm/20230228213738.272178-1-willy@xxxxxxxxxxxxx/T/#m84673899e25bc31356093a1177941f2cc35e5da8
FYI, I'm seeing a perf regression of about 1% when compiling the kernel on
Ampere Altra (arm64) with this whole series on top of v6.3-rc1 (In a VM using
ext4 filesystem). Looks like instruction aborts are taking much longer and a
selection of syscalls are a bit slower. Still hunting down the root cause. Will
report once I have conclusive diagnosis.
Thanks,
Ryan
> + }
> +
> + if (first)
> + nr++;
> + } while (page++, --nr_pages > 0);
> } else if (folio_test_pmd_mappable(folio)) {
> /* That test is redundant: it's for safety or to optimize out */
>
> @@ -1354,6 +1362,30 @@ void page_add_file_rmap(struct page *page, struct vm_area_struct *vma,
> mlock_vma_folio(folio, vma, compound);
> }
>
> +/**
> + * page_add_file_rmap - add pte mapping to a file page
> + * @page: the page to add the mapping to
> + * @vma: the vm area in which the mapping is added
> + * @compound: charge the page as compound or small page
> + *
> + * The caller needs to hold the pte lock.
> + */
> +void page_add_file_rmap(struct page *page, struct vm_area_struct *vma,
> + bool compound)
> +{
> + struct folio *folio = page_folio(page);
> + unsigned int nr_pages;
> +
> + VM_WARN_ON_ONCE_PAGE(compound && !PageTransHuge(page), page);
> +
> + if (likely(!compound))
> + nr_pages = 1;
> + else
> + nr_pages = folio_nr_pages(folio);
> +
> + folio_add_file_rmap_range(folio, page, nr_pages, vma, compound);
> +}
> +
> /**
> * page_remove_rmap - take down pte mapping from a page
> * @page: page to remove mapping from
