On 10/09/2014 02:19 AM, Fengwei Yin wrote:
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index 80ca4fb..8550b27 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -476,7 +476,7 @@ static void smaps_pte_entry(pte_t ptent, unsigned long addr,
> mss->nonlinear += ptent_size;
> }
>
> - if (!page)
> + if (!page || is_huge_zero_page(page))
> return;
This really seems like a bit of a hack. A normal (small) zero page
won't make it to this point because of the vm_normal_page() check in
smaps_pte_entry() which hits the _PAGE_SPECIAL bit in the pte.
Is there a reason we can't set _PAGE_SPECIAL on the huge_zero_page ptes?
If we did that, we wouldn't need a special case here.
If we can't do that for some reason, can we at least teach
vm_normal_page() about the huge_zero_page in some other way?
> if (PageAnon(page))
> @@ -516,7 +516,8 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
> if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
> smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
> spin_unlock(ptl);
> - mss->anonymous_thp += HPAGE_PMD_SIZE;
> + if (!is_huge_zero_pmd(*pmd))
> + mss->anonymous_thp += HPAGE_PMD_SIZE;
> return 0;
> }
How about we just move this hunk in to smaps_pte_entry()? Something
along these lines:
...
if (PageAnon(page)) {
mss->anonymous += ptent_size;
+ if (PageTransHuge(page))
+ mss->anonymous_thp += ptent_size;
}
If we do that, plus teaching vm_normal_page() about huge_zero_pages, it
will help keep the hacks and the extra code due to huge pages to a miniumum.
> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
> index 63579cb..758f569 100644
> --- a/include/linux/huge_mm.h
> +++ b/include/linux/huge_mm.h
> @@ -34,6 +34,10 @@ extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
> unsigned long addr, pgprot_t newprot,
> int prot_numa);
>
> +extern bool is_huge_zero_page(struct page *page);
> +
> +extern bool is_huge_zero_pmd(pmd_t pmd);
> +
> enum transparent_hugepage_flag {
> TRANSPARENT_HUGEPAGE_FLAG,
> TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index d9a21d06..bedc3ae 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -173,12 +173,12 @@ static int start_khugepaged(void)
> static atomic_t huge_zero_refcount;
> static struct page *huge_zero_page __read_mostly;
>
> -static inline bool is_huge_zero_page(struct page *page)
> +bool is_huge_zero_page(struct page *page)
> {
> return ACCESS_ONCE(huge_zero_page) == page;
> }
>
> -static inline bool is_huge_zero_pmd(pmd_t pmd)
> +bool is_huge_zero_pmd(pmd_t pmd)
> {
> return is_huge_zero_page(pmd_page(pmd));
> }
^^^ And all these exports.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>