On Tue, Mar 8, 2022 at 1:35 PM Zach O'Keefe <zokeefe@xxxxxxxxxx> wrote:
>
> In madvise collapse context, we optionally want to be able to ignore
> advice from MADV_NOHUGEPAGE-marked regions.
Could you please elaborate why this usecase is valid? Typically
MADV_NOHUGEPAGE is set when the users really don't want to have THP
for this area. So it doesn't make too much sense to ignore it IMHO.
>
> Add a vm_flags_ignore argument to hugepage_vma_revalidate_pmd_count()
> which can be used to ignore vm flags used when considering thp
> eligibility.
>
> Signed-off-by: Zach O'Keefe <zokeefe@xxxxxxxxxx>
> ---
> mm/khugepaged.c | 18 ++++++++++++------
> 1 file changed, 12 insertions(+), 6 deletions(-)
>
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index 1d20be47bcea..ecbd3fc41c80 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -964,10 +964,14 @@ khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node)
> #endif
>
> /*
> - * Revalidate a vma's eligibility to collapse nr hugepages.
> + * Revalidate a vma's eligibility to collapse nr hugepages. vm_flags_ignore
> + * can be used to ignore certain vma_flags that would otherwise be checked -
> + * the principal example being VM_NOHUGEPAGE which is ignored in madvise
> + * collapse context.
> */
> static int hugepage_vma_revalidate_pmd_count(struct mm_struct *mm,
> unsigned long address, int nr,
> + unsigned long vm_flags_ignore,
> struct vm_area_struct **vmap)
> {
> struct vm_area_struct *vma;
> @@ -986,7 +990,7 @@ static int hugepage_vma_revalidate_pmd_count(struct mm_struct *mm,
> hend = vma->vm_end & HPAGE_PMD_MASK;
> if (address < hstart || (address + nr * HPAGE_PMD_SIZE) > hend)
> return SCAN_ADDRESS_RANGE;
> - if (!hugepage_vma_check(vma, vma->vm_flags))
> + if (!hugepage_vma_check(vma, vma->vm_flags & ~vm_flags_ignore))
> return SCAN_VMA_CHECK;
> /* Anon VMA expected */
> if (!vma->anon_vma || vma->vm_ops)
> @@ -1000,9 +1004,11 @@ static int hugepage_vma_revalidate_pmd_count(struct mm_struct *mm,
> */
>
> static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
> + unsigned long vm_flags_ignore,
> struct vm_area_struct **vmap)
> {
> - return hugepage_vma_revalidate_pmd_count(mm, address, 1, vmap);
> + return hugepage_vma_revalidate_pmd_count(mm, address, 1,
> + vm_flags_ignore, vmap);
> }
>
> /*
> @@ -1043,7 +1049,7 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
> /* do_swap_page returns VM_FAULT_RETRY with released mmap_lock */
> if (ret & VM_FAULT_RETRY) {
> mmap_read_lock(mm);
> - if (hugepage_vma_revalidate(mm, haddr, &vma)) {
> + if (hugepage_vma_revalidate(mm, haddr, VM_NONE, &vma)) {
> /* vma is no longer available, don't continue to swapin */
> trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
> return false;
> @@ -1200,7 +1206,7 @@ static void collapse_huge_page(struct mm_struct *mm,
> count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC);
>
> mmap_read_lock(mm);
> - result = hugepage_vma_revalidate(mm, address, &vma);
> + result = hugepage_vma_revalidate(mm, address, VM_NONE, &vma);
> if (result) {
> mmap_read_unlock(mm);
> goto out_nolock;
> @@ -1232,7 +1238,7 @@ static void collapse_huge_page(struct mm_struct *mm,
> */
> mmap_write_lock(mm);
>
> - result = hugepage_vma_revalidate(mm, address, &vma);
> + result = hugepage_vma_revalidate(mm, address, VM_NONE, &vma);
> if (result)
> goto out_up_write;
> /* check if the pmd is still valid */
> --
> 2.35.1.616.g0bdcbb4464-goog
>
