[3.8.y.z,extended,stable] Patch "mm: Close races between THP migration and PMD numa clearing" has been added to staging queue

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1390fdd..9c37776 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1323,24 +1323,25 @@  int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	target_nid = mpol_misplaced(page, vma, haddr);
 	if (target_nid == -1) {
 		/* If the page was locked, there are no parallel migrations */
-		if (page_locked) {
-			unlock_page(page);
+		if (page_locked)
 			goto clear_pmdnuma;
-		}

-		/* Otherwise wait for potential migrations and retry fault */
+		/*
+		 * 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.
+		 */
 		spin_unlock(&mm->page_table_lock);
 		wait_on_page_locked(page);
+		page_nid = -1;
 		goto out;
 	}

 	/* Page is misplaced, serialise migrations and parallel THP splits */
 	get_page(page);
 	spin_unlock(&mm->page_table_lock);
-	if (!page_locked) {
+	if (!page_locked)
 		lock_page(page);
-		page_locked = true;
-	}
 	anon_vma = page_lock_anon_vma_read(page);

 	/* Confirm the PTE did not while locked */
@@ -1348,29 +1349,29 @@  int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(!pmd_same(pmd, *pmdp))) {
 		unlock_page(page);
 		put_page(page);
+		page_nid = -1;
 		goto out_unlock;
 	}

-	/* Migrate the THP to the requested node */
+	/*
+	 * Migrate the THP to the requested node, returns with page unlocked
+	 * and pmd_numa cleared.
+	 */
 	spin_unlock(&mm->page_table_lock);
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
 				pmdp, pmd, addr, page, target_nid);
 	if (migrated)
 		page_nid = target_nid;
-	else
-		goto check_same;

 	goto out;

-check_same:
-	spin_lock(&mm->page_table_lock);
-	if (unlikely(!pmd_same(pmd, *pmdp)))
-		goto out_unlock;
 clear_pmdnuma:
+	BUG_ON(!PageLocked(page));
 	pmd = pmd_mknonnuma(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	VM_BUG_ON(pmd_numa(*pmdp));
 	update_mmu_cache_pmd(vma, addr, pmdp);
+	unlock_page(page);
 out_unlock:
 	spin_unlock(&mm->page_table_lock);

diff --git a/mm/migrate.c b/mm/migrate.c
index 811a2ca..d2296c5 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1725,12 +1725,12 @@  int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		unlock_page(new_page);
 		put_page(new_page);		/* Free it */

-		unlock_page(page);
+		/* Retake the callers reference and putback on LRU */
+		get_page(page);
 		putback_lru_page(page);
-
-		count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
-		isolated = 0;
-		goto out;
+		mod_zone_page_state(page_zone(page),
+			 NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
+		goto out_fail;
 	}

 	/*
@@ -1747,9 +1747,9 @@  int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 	entry = pmd_mkhuge(entry);

-	page_add_new_anon_rmap(new_page, vma, haddr);
-
+	pmdp_clear_flush(vma, haddr, pmd);
 	set_pmd_at(mm, haddr, pmd, entry);
+	page_add_new_anon_rmap(new_page, vma, haddr);
 	update_mmu_cache_pmd(vma, address, &entry);
 	page_remove_rmap(page);
 	/*
@@ -1768,7 +1768,6 @@  int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
 	count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);

-out:
 	mod_zone_page_state(page_zone(page),
 			NR_ISOLATED_ANON + page_lru,
 			-HPAGE_PMD_NR);
@@ -1777,6 +1776,10 @@  out:
 out_fail:
 	count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
 out_dropref:
+	entry = pmd_mknonnuma(entry);
+	set_pmd_at(mm, haddr, pmd, entry);
+	update_mmu_cache_pmd(vma, address, &entry);
+
 	unlock_page(page);
 	put_page(page);
 	return 0;