We still call try_grab_folio() once per PTE; a future patch could
optimise to just adjust the reference count for each page within
the folio.
Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
---
mm/gup.c | 16 +++++++---------
1 file changed, 7 insertions(+), 9 deletions(-)
diff --git a/mm/gup.c b/mm/gup.c
index c3e514172eaf..27cc097ec05d 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2235,7 +2235,8 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
ptem = ptep = pte_offset_map(&pmd, addr);
do {
pte_t pte = ptep_get_lockless(ptep);
- struct page *head, *page;
+ struct page *page;
+ struct folio *folio;
/*
* Similar to the PMD case below, NUMA hinting must take slow
@@ -2262,22 +2263,20 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
page = pte_page(pte);
- head = try_grab_compound_head(page, 1, flags);
- if (!head)
+ folio = try_grab_folio(page, 1, flags);
+ if (!folio)
goto pte_unmap;
if (unlikely(page_is_secretmem(page))) {
- put_compound_head(head, 1, flags);
+ gup_put_folio(folio, 1, flags);
goto pte_unmap;
}
if (unlikely(pte_val(pte) != pte_val(*ptep))) {
- put_compound_head(head, 1, flags);
+ gup_put_folio(folio, 1, flags);
goto pte_unmap;
}
- VM_BUG_ON_PAGE(compound_head(page) != head, page);
-
/*
* We need to make the page accessible if and only if we are
* going to access its content (the FOLL_PIN case). Please
@@ -2291,10 +2290,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
goto pte_unmap;
}
}
- SetPageReferenced(page);
+ folio_set_referenced(folio);
pages[*nr] = page;
(*nr)++;
-
} while (ptep++, addr += PAGE_SIZE, addr != end);
ret = 1;
--
2.33.0
On Mon, Jan 10, 2022 at 04:23:58AM +0000, Matthew Wilcox (Oracle) wrote:
> We still call try_grab_folio() once per PTE; a future patch could
> optimise to just adjust the reference count for each page within
> the folio.
Looks good,
Reviewed-by: Christoph Hellwig <[email protected]>
On 1/9/22 20:23, Matthew Wilcox (Oracle) wrote:
> We still call try_grab_folio() once per PTE; a future patch could
> optimise to just adjust the reference count for each page within
> the folio.
>
> Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
> ---
> mm/gup.c | 16 +++++++---------
> 1 file changed, 7 insertions(+), 9 deletions(-)
Still looks good.
Reviewed-by: John Hubbard <[email protected]>
thanks,
--
John Hubbard
NVIDIA
>
> diff --git a/mm/gup.c b/mm/gup.c
> index c3e514172eaf..27cc097ec05d 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -2235,7 +2235,8 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
> ptem = ptep = pte_offset_map(&pmd, addr);
> do {
> pte_t pte = ptep_get_lockless(ptep);
> - struct page *head, *page;
> + struct page *page;
> + struct folio *folio;
>
> /*
> * Similar to the PMD case below, NUMA hinting must take slow
> @@ -2262,22 +2263,20 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
> VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
> page = pte_page(pte);
>
> - head = try_grab_compound_head(page, 1, flags);
> - if (!head)
> + folio = try_grab_folio(page, 1, flags);
> + if (!folio)
> goto pte_unmap;
>
> if (unlikely(page_is_secretmem(page))) {
> - put_compound_head(head, 1, flags);
> + gup_put_folio(folio, 1, flags);
> goto pte_unmap;
> }
>
> if (unlikely(pte_val(pte) != pte_val(*ptep))) {
> - put_compound_head(head, 1, flags);
> + gup_put_folio(folio, 1, flags);
> goto pte_unmap;
> }
>
> - VM_BUG_ON_PAGE(compound_head(page) != head, page);
> -
> /*
> * We need to make the page accessible if and only if we are
> * going to access its content (the FOLL_PIN case). Please
> @@ -2291,10 +2290,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
> goto pte_unmap;
> }
> }
> - SetPageReferenced(page);
> + folio_set_referenced(folio);
> pages[*nr] = page;
> (*nr)++;
> -
> } while (ptep++, addr += PAGE_SIZE, addr != end);
>
> ret = 1;