On Tue, Feb 28, 2023 at 09:37:33PM +0000, Matthew Wilcox (Oracle) wrote:
> Push the iteration over each page down to the architectures (many
> can flush the entire THP without iteration).
>
> Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
> ---
> mm/memory.c | 3 +--
> 1 file changed, 1 insertion(+), 2 deletions(-)
>
> diff --git a/mm/memory.c b/mm/memory.c
> index bfa3100ec5a3..69e844d5f75c 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -4222,8 +4222,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
> if (unlikely(!pmd_none(*vmf->pmd)))
> goto out;
>
> - for (i = 0; i < HPAGE_PMD_NR; i++)
> - flush_icache_page(vma, page + i);
> + flush_icache_pages(vma, page, HPAGE_PMD_NR);
>
> entry = mk_huge_pmd(page, vma->vm_page_prot);
> if (write)
> --
> 2.39.1
I get this:
CC mm/memory.o
/home/mike/git/linux/mm/memory.c: In function 'do_set_pmd':
/home/mike/git/linux/mm/memory.c:4191:13: warning: unused variable 'i' [-Wunused-variable]
4191 | int i;
| ^
And the patch here makes it go away:
diff --git a/mm/memory.c b/mm/memory.c
index cc7845ff09ba..c359fb8643e5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4188,7 +4188,6 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
bool write = vmf->flags & FAULT_FLAG_WRITE;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
pmd_t entry;
- int i;
vm_fault_t ret = VM_FAULT_FALLBACK;
if (!transhuge_vma_suitable(vma, haddr))
--
Sincerely yours,
Mike.
