On 05/23/2018 05:58 PM, Huang, Ying wrote: > From: Huang Ying <[email protected]> > > 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" <[email protected]>
Reviewed-by: Mike Kravetz <[email protected]> -- Mike Kravetz > Cc: Mike Kravetz <[email protected]> > Cc: Michal Hocko <[email protected]> > Cc: David Rientjes <[email protected]> > Cc: Andrea Arcangeli <[email protected]> > Cc: "Kirill A. Shutemov" <[email protected]> > Cc: Andi Kleen <[email protected]> > Cc: Jan Kara <[email protected]> > Cc: Matthew Wilcox <[email protected]> > Cc: Hugh Dickins <[email protected]> > Cc: Minchan Kim <[email protected]> > Cc: Shaohua Li <[email protected]> > Cc: Christopher Lameter <[email protected]> > Cc: "Aneesh Kumar K.V" <[email protected]> > Cc: Punit Agrawal <[email protected]> > Cc: Anshuman Khandual <[email protected]> > --- > 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; > } >
