mm, hugetlbfs: pass fault address to cow handler

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.

Link: http://lkml.kernel.org/r/20180524005851.4079-5-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andi Kleen <andi.kleen@intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Shaohua Li <shli@fb.com>
Cc: Christopher Lameter <cl@linux.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Punit Agrawal <punit.agrawal@arm.com>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e6767a35f7de12a67d1b6c9367163209bbe97773..f1bcaae0d73a7114e683d132c462b467f9e2725f 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3509,7 +3509,7 @@ 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;
@@ -3518,6 +3518,7 @@ 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);
@@ -3592,7 +3593,7 @@ retry_avoidcopy:
                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);
@@ -3826,7 +3827,7 @@ retry:
        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);
@@ -3980,7 +3981,7 @@ 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;
                }