Re: [PATCH -V2 -mm 4/4] mm, hugetlbfs: Pass fault address to cow handler

[Mike Kravetz]

On 05/23/2018 05:58 PM, Huang, Ying wrote:
> From: Huang Ying <ying.huang@xxxxxxxxx>
> 
> This is to take better advantage of the general huge page copying
> optimization.  Where, the target subpage will be copied last to avoid
> the cache lines of target subpage to be evicted when copying other
> subpages.  This works better if the address of the target subpage is
> available when copying huge page.  So hugetlbfs page fault handlers
> are changed to pass that information to hugetlb_cow().  This will
> benefit workloads which don't access the begin of the hugetlbfs huge
> page after the page fault under heavy cache contention.
> 
> Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx>

Reviewed-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
-- 
Mike Kravetz

> Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
> Cc: Michal Hocko <mhocko@xxxxxxxx>
> Cc: David Rientjes <rientjes@xxxxxxxxxx>
> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
> Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
> Cc: Andi Kleen <andi.kleen@xxxxxxxxx>
> Cc: Jan Kara <jack@xxxxxxx>
> Cc: Matthew Wilcox <mawilcox@xxxxxxxxxxxxx>
> Cc: Hugh Dickins <hughd@xxxxxxxxxx>
> Cc: Minchan Kim <minchan@xxxxxxxxxx>
> Cc: Shaohua Li <shli@xxxxxx>
> Cc: Christopher Lameter <cl@xxxxxxxxx>
> Cc: "Aneesh Kumar K.V" <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
> Cc: Punit Agrawal <punit.agrawal@xxxxxxx>
> Cc: Anshuman Khandual <khandual@xxxxxxxxxxxxxxxxxx>
> ---
>  mm/hugetlb.c | 9 +++++----
>  1 file changed, 5 insertions(+), 4 deletions(-)
> 
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index ad3bec2ed269..1df974af34c1 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -3500,7 +3500,7 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
>   * Keep the pte_same checks anyway to make transition from the mutex easier.
>   */
>  static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
> -		       unsigned long haddr, pte_t *ptep,
> +		       unsigned long address, pte_t *ptep,
>  		       struct page *pagecache_page, spinlock_t *ptl)
>  {
>  	pte_t pte;
> @@ -3509,6 +3509,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
>  	int ret = 0, outside_reserve = 0;
>  	unsigned long mmun_start;	/* For mmu_notifiers */
>  	unsigned long mmun_end;		/* For mmu_notifiers */
> +	unsigned long haddr = address & huge_page_mask(h);
>  
>  	pte = huge_ptep_get(ptep);
>  	old_page = pte_page(pte);
> @@ -3583,7 +3584,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
>  		goto out_release_all;
>  	}
>  
> -	copy_user_huge_page(new_page, old_page, haddr, vma,
> +	copy_user_huge_page(new_page, old_page, address, vma,
>  			    pages_per_huge_page(h));
>  	__SetPageUptodate(new_page);
>  	set_page_huge_active(new_page);
> @@ -3817,7 +3818,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
>  	hugetlb_count_add(pages_per_huge_page(h), mm);
>  	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
>  		/* Optimization, do the COW without a second fault */
> -		ret = hugetlb_cow(mm, vma, haddr, ptep, page, ptl);
> +		ret = hugetlb_cow(mm, vma, address, ptep, page, ptl);
>  	}
>  
>  	spin_unlock(ptl);
> @@ -3971,7 +3972,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
>  
>  	if (flags & FAULT_FLAG_WRITE) {
>  		if (!huge_pte_write(entry)) {
> -			ret = hugetlb_cow(mm, vma, haddr, ptep,
> +			ret = hugetlb_cow(mm, vma, address, ptep,
>  					  pagecache_page, ptl);
>  			goto out_put_page;
>  		}
>