[PATCH] thp: add option to setup migration entries during PMD split

[Kirill A. Shutemov]

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@xxxxxxxxxxxxxxx>
Tested-by: Sasha Levin <sasha.levin@xxxxxxxxxx>
Tested-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Acked-by: Vlastimil Babka <vbabka@xxxxxxx>
Acked-by: Jerome Marchand <jmarchan@xxxxxxxxxx>
---
 mm/huge_memory.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1e0e02786241..0d817863a739 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -25,6 +25,7 @@
 #include <linux/migrate.h>
 #include <linux/hashtable.h>
 #include <linux/userfaultfd_k.h>
+#include <linux/swapops.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -2627,7 +2628,7 @@ 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;
@@ -2669,12 +2670,18 @@ 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);
@@ -2715,7 +2722,7 @@ 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);
 }
-- 
 Kirill A. Shutemov
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/