thp: add option to setup migration entries during PMD split

We are going to use migration PTE entries to stabilize page counts.  If
the page is mapped with PMDs we need to split the PMD and setup
migration entries.  It's reasonable to combine these operations to avoid
double-scanning over the page table.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 22ab365cce52e7d77eb6c64c726c89c8d70e5dd2..913559388fda3640387a237670a334b7aa2074a5 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2695,7 +2695,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 }
 
 static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
-               unsigned long haddr)
+               unsigned long haddr, bool freeze)
 {
        struct mm_struct *mm = vma->vm_mm;
        struct page *page;
@@ -2739,12 +2739,18 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
                 * transferred to avoid any possibility of altering
                 * permissions across VMAs.
                 */
-               entry = mk_pte(page + i, vma->vm_page_prot);
-               entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-               if (!write)
-                       entry = pte_wrprotect(entry);
-               if (!young)
-                       entry = pte_mkold(entry);
+               if (freeze) {
+                       swp_entry_t swp_entry;
+                       swp_entry = make_migration_entry(page + i, write);
+                       entry = swp_entry_to_pte(swp_entry);
+               } else {
+                       entry = mk_pte(page + i, vma->vm_page_prot);
+                       entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+                       if (!write)
+                               entry = pte_wrprotect(entry);
+                       if (!young)
+                               entry = pte_mkold(entry);
+               }
                pte = pte_offset_map(&_pmd, haddr);
                BUG_ON(!pte_none(*pte));
                set_pte_at(mm, haddr, pte, entry);
@@ -2785,7 +2791,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
        mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE);
        ptl = pmd_lock(mm, pmd);
        if (likely(pmd_trans_huge(*pmd)))
-               __split_huge_pmd_locked(vma, pmd, haddr);
+               __split_huge_pmd_locked(vma, pmd, haddr, false);
        spin_unlock(ptl);
        mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PMD_SIZE);
 }