mm: migrate: add hugepage migration code to move_pages()

Extend move_pages() to handle vma with VM_HUGETLB set.  We will be able to
migrate hugepage with move_pages(2) after applying the enablement patch
which comes later in this series.

We avoid getting refcount on tail pages of hugepage, because unlike thp,
hugepage is not split and we need not care about races with splitting.

And migration of larger (1GB for x86_64) hugepage are not enabled.

Signed-off-by: Naoya Horiguchi <[email protected]>
Acked-by: Andi Kleen <[email protected]>
Reviewed-by: Wanpeng Li <[email protected]>
Cc: Hillf Danton <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: KOSAKI Motohiro <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: "Aneesh Kumar K.V" <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

mm/memory.c

@@ -1481,7 +1481,8 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	if (pud_none(*pud))
 		goto no_page_table;
 	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
-		BUG_ON(flags & FOLL_GET);
+		if (flags & FOLL_GET)
+			goto out;
 		page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
 		goto out;
 	}
@@ -1492,8 +1493,20 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	if (pmd_none(*pmd))
 		goto no_page_table;
 	if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
-		BUG_ON(flags & FOLL_GET);
 		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
+		if (flags & FOLL_GET) {
+			/*
+			 * Refcount on tail pages are not well-defined and
+			 * shouldn't be taken. The caller should handle a NULL
+			 * return when trying to follow tail pages.
+			 */
+			if (PageHead(page))
+				get_page(page);
+			else {
+				page = NULL;
+				goto out;
+			}
+		}
 		goto out;
 	}
 	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))

mm/migrate.c

@@ -1092,7 +1092,11 @@ static struct page *new_page_node(struct page *p, unsigned long private,
 
 	*result = &pm->status;
 
-	return alloc_pages_exact_node(pm->node,
+	if (PageHuge(p))
+		return alloc_huge_page_node(page_hstate(compound_head(p)),
+					pm->node);
+	else
+		return alloc_pages_exact_node(pm->node,
 				GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
 }
 
@@ -1152,6 +1156,11 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
 				!migrate_all)
 			goto put_and_set;
 
+		if (PageHuge(page)) {
+			isolate_huge_page(page, &pagelist);
+			goto put_and_set;
+		}
+
 		err = isolate_lru_page(page);
 		if (!err) {
 			list_add_tail(&page->lru, &pagelist);
@@ -1174,7 +1183,7 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
 		err = migrate_pages(&pagelist, new_page_node,
 				(unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL);
 		if (err)
-			putback_lru_pages(&pagelist);
+			putback_movable_pages(&pagelist);
 	}
 
 	up_read(&mm->mmap_sem);