mm: numa: do not clear PMD during PTE update scan

[platform/adaptation/renesas_rcar/renesas_kernel.git] / mm / huge_memory.c

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 33a5dc4..420826e 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1243,6 +1243,10 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
        if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
                return ERR_PTR(-EFAULT);
 
+       /* Full NUMA hinting faults to serialise migration in fault paths */
+       if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+               goto out;
+
        page = pmd_page(*pmd);
        VM_BUG_ON(!PageHead(page));
        if (flags & FOLL_TOUCH) {
@@ -1323,23 +1327,27 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                /* If the page was locked, there are no parallel migrations */
                if (page_locked)
                        goto clear_pmdnuma;
+       }
 
-               /*
-                * Otherwise wait for potential migrations and retry. We do
-                * relock and check_same as the page may no longer be mapped.
-                * As the fault is being retried, do not account for it.
-                */
+       /*
+        * If there are potential migrations, wait for completion and retry. We
+        * do not relock and check_same as the page may no longer be mapped.
+        * Furtermore, even if the page is currently misplaced, there is no
+        * guarantee it is still misplaced after the migration completes.
+        */
+       if (!page_locked) {
                spin_unlock(ptl);
                wait_on_page_locked(page);
                page_nid = -1;
                goto out;
        }
 
-       /* Page is misplaced, serialise migrations and parallel THP splits */
+       /*
+        * Page is misplaced. Page lock serialises migrations. Acquire anon_vma
+        * to serialises splits
+        */
        get_page(page);
        spin_unlock(ptl);
-       if (!page_locked)
-               lock_page(page);
        anon_vma = page_lock_anon_vma_read(page);
 
        /* Confirm the PMD did not change while page_table_lock was released */
@@ -1531,7 +1539,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
                         */
                        if (!is_huge_zero_page(page) &&
                            !pmd_numa(*pmd)) {
-                               entry = pmdp_get_and_clear(mm, addr, pmd);
+                               entry = *pmd;
                                entry = pmd_mknuma(entry);
                                ret = HPAGE_PMD_NR;
                        }