[PATCH 4/8] migrate: add hugepage migration code to move_pages()

[Naoya Horiguchi]

This patch extends 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.

ChangeLog v3:
 - revert introducing migrate_movable_pages
 - follow_page_mask(FOLL_GET) returns NULL for tail pages
 - use isolate_huge_page

ChangeLog v2:
 - updated description and renamed patch title

Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
---
 mm/memory.c  | 12 ++++++++++--
 mm/migrate.c | 13 +++++++++++--
 2 files changed, 21 insertions(+), 4 deletions(-)

diff --git v3.11-rc1.orig/mm/memory.c v3.11-rc1/mm/memory.c
index 1ce2e2a..8c9a2cb 100644
--- v3.11-rc1.orig/mm/memory.c
+++ v3.11-rc1/mm/memory.c
@@ -1496,7 +1496,8 @@ 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;
 	}
@@ -1507,8 +1508,15 @@ 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) {
+			if (PageHead(page))
+				get_page_foll(page);
+			else {
+				page = NULL;
+				goto out;
+			}
+		}
 		goto out;
 	}
 	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
diff --git v3.11-rc1.orig/mm/migrate.c v3.11-rc1/mm/migrate.c
index 3ec47d3..d313737 100644
--- v3.11-rc1.orig/mm/migrate.c
+++ v3.11-rc1/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);
-- 
1.8.3.1

--
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/